diff --git a/aana/tests/files/cache/VLLMDeployment/chat_stream_90417c2a15b76361a6b09dbd7619d9e4_46de8476435df430f5c78286fc65f186.pkl b/aana/tests/files/cache/VLLMDeployment/chat_stream_90417c2a15b76361a6b09dbd7619d9e4_46de8476435df430f5c78286fc65f186.pkl
new file mode 100644
index 00000000..ad2ec4ca
Binary files /dev/null and b/aana/tests/files/cache/VLLMDeployment/chat_stream_90417c2a15b76361a6b09dbd7619d9e4_46de8476435df430f5c78286fc65f186.pkl differ
diff --git a/aana/tests/files/cache/VLLMDeployment/generate_stream_90417c2a15b76361a6b09dbd7619d9e4_4593940d30bd951f50ec6df6aa1c6a49.pkl b/aana/tests/files/cache/VLLMDeployment/generate_stream_90417c2a15b76361a6b09dbd7619d9e4_4593940d30bd951f50ec6df6aa1c6a49.pkl
new file mode 100644
index 00000000..23cb3ea4
Binary files /dev/null and b/aana/tests/files/cache/VLLMDeployment/generate_stream_90417c2a15b76361a6b09dbd7619d9e4_4593940d30bd951f50ec6df6aa1c6a49.pkl differ
diff --git a/aana/tests/files/cache/WhisperDeployment/transcribe_2e11e31958b0bf482389e1adf3420c4d_16816f10f770816669f6d2a71e631077.pkl b/aana/tests/files/cache/WhisperDeployment/transcribe_2e11e31958b0bf482389e1adf3420c4d_16816f10f770816669f6d2a71e631077.pkl
index 7207ce36..ce82f981 100644
Binary files a/aana/tests/files/cache/WhisperDeployment/transcribe_2e11e31958b0bf482389e1adf3420c4d_16816f10f770816669f6d2a71e631077.pkl and b/aana/tests/files/cache/WhisperDeployment/transcribe_2e11e31958b0bf482389e1adf3420c4d_16816f10f770816669f6d2a71e631077.pkl differ
diff --git a/aana/tests/files/cache/WhisperDeployment/transcribe_2e11e31958b0bf482389e1adf3420c4d_612d535de3401a5cc19e02611669f370.pkl b/aana/tests/files/cache/WhisperDeployment/transcribe_2e11e31958b0bf482389e1adf3420c4d_612d535de3401a5cc19e02611669f370.pkl
index 93302296..965a6f80 100644
Binary files a/aana/tests/files/cache/WhisperDeployment/transcribe_2e11e31958b0bf482389e1adf3420c4d_612d535de3401a5cc19e02611669f370.pkl and b/aana/tests/files/cache/WhisperDeployment/transcribe_2e11e31958b0bf482389e1adf3420c4d_612d535de3401a5cc19e02611669f370.pkl differ
diff --git a/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_612d535de3401a5cc19e02611669f370.pkl b/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_612d535de3401a5cc19e02611669f370.pkl
index d0a531cb..5ebb19a9 100644
Binary files a/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_612d535de3401a5cc19e02611669f370.pkl and b/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_612d535de3401a5cc19e02611669f370.pkl differ
diff --git a/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_7a46ac1e8d8346f6180e62f9d737ed16.pkl b/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_6362b20898011471e20b6a983f24a964.pkl
similarity index 50%
rename from aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_7a46ac1e8d8346f6180e62f9d737ed16.pkl
rename to aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_6362b20898011471e20b6a983f24a964.pkl
index 8e45192a..42a2cce6 100644
Binary files a/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_7a46ac1e8d8346f6180e62f9d737ed16.pkl and b/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_6362b20898011471e20b6a983f24a964.pkl differ
diff --git a/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_66a38087fcdd81f03fe4446f72f5ee8c.pkl b/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_63c144aae2072ad3f161e8c042eb9841.pkl
similarity index 63%
rename from aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_66a38087fcdd81f03fe4446f72f5ee8c.pkl
rename to aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_63c144aae2072ad3f161e8c042eb9841.pkl
index f762a73b..360db455 100644
Binary files a/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_66a38087fcdd81f03fe4446f72f5ee8c.pkl and b/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_63c144aae2072ad3f161e8c042eb9841.pkl differ
diff --git a/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_7e8ed7a39f48a499b224b7f6be2bfb7f.pkl b/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_7d0f073589d0c2fb0fff91dba3f33d44.pkl
similarity index 53%
rename from aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_7e8ed7a39f48a499b224b7f6be2bfb7f.pkl
rename to aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_7d0f073589d0c2fb0fff91dba3f33d44.pkl
index 494d34d2..e1562e82 100644
Binary files a/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_7e8ed7a39f48a499b224b7f6be2bfb7f.pkl and b/aana/tests/files/cache/WhisperDeployment/transcribe_stream_2e11e31958b0bf482389e1adf3420c4d_7d0f073589d0c2fb0fff91dba3f33d44.pkl differ
diff --git a/aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_66c00451959f743fb90124400142c05b.json b/aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_25de6d61bbd9ec569859212bd075855f.json
similarity index 90%
rename from aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_66c00451959f743fb90124400142c05b.json
rename to aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_25de6d61bbd9ec569859212bd075855f.json
index 2aa5e414..a7d26e92 100644
--- a/aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_66c00451959f743fb90124400142c05b.json
+++ b/aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_25de6d61bbd9ec569859212bd075855f.json
@@ -6,7 +6,7 @@
         },
         "segments": [
             {
-                "confidence": 0.6239854156762731,
+                "confidence": 0.6237288876411261,
                 "no_speech_confidence": 0.4189453125,
                 "text": " We're no strangers to love You know the rules, and so do I",
                 "time_interval": {
@@ -20,6 +20,28 @@
             "text": " We're no strangers to love You know the rules, and so do I"
         }
     },
+    {
+        "captions": [
+            "a black background with a white background",
+            "a man with his eyes closed singing into a microphone",
+            "a man in a suit is singing into a microphone",
+            "a person is holding a black jacket and a white shirt",
+            "a man in a suit is singing into a microphone",
+            "a man is smiling and wearing a white jacket",
+            "a man in a white coat is standing in front of a brick wall",
+            "a man in a white coat is standing in front of a brick wall"
+        ],
+        "timestamps": [
+            0.0,
+            0.07999999821186066,
+            0.6800000071525574,
+            2.0,
+            5.320000171661377,
+            7.440000057220459,
+            7.960000038146973,
+            8.760000228881836
+        ]
+    },
     {
         "info": {
             "language": "en",
@@ -27,8 +49,8 @@
         },
         "segments": [
             {
-                "confidence": 0.8495449356404748,
-                "no_speech_confidence": 0.72900390625,
+                "confidence": 0.8493308731843703,
+                "no_speech_confidence": 0.7255859375,
                 "text": " I feel commitments while I'm thinking of You wouldn't get this from any other guy",
                 "time_interval": {
                     "end": 34.879999999999995,
@@ -48,8 +70,8 @@
         },
         "segments": [
             {
-                "confidence": 0.8495449356404748,
-                "no_speech_confidence": 0.72900390625,
+                "confidence": 0.8493308731843703,
+                "no_speech_confidence": 0.7255859375,
                 "text": " I just wanna tell you how I'm feeling Gotta make you understand",
                 "time_interval": {
                     "end": 42.879999999999995,
@@ -69,8 +91,8 @@
         },
         "segments": [
             {
-                "confidence": 0.8495449356404748,
-                "no_speech_confidence": 0.72900390625,
+                "confidence": 0.8493308731843703,
+                "no_speech_confidence": 0.7255859375,
                 "text": " Never gonna give you up Never gonna let you down",
                 "time_interval": {
                     "end": 46.879999999999995,
@@ -90,8 +112,8 @@
         },
         "segments": [
             {
-                "confidence": 0.8495449356404748,
-                "no_speech_confidence": 0.72900390625,
+                "confidence": 0.8493308731843703,
+                "no_speech_confidence": 0.7255859375,
                 "text": " Never gonna run around and desert you Never gonna make you cry",
                 "time_interval": {
                     "end": 52.879999999999995,
@@ -104,28 +126,6 @@
             "text": " Never gonna run around and desert you Never gonna make you cry"
         }
     },
-    {
-        "captions": [
-            "a black background with a white background",
-            "a man in a suit is singing into a microphone",
-            "a man in a suit is singing into a microphone",
-            "a person is holding a black jacket and a white shirt",
-            "a man in a suit is singing into a microphone",
-            "a man is smiling and wearing a white jacket",
-            "a man in a white coat is standing in front of a brick wall",
-            "a man in a white coat is standing in front of a brick wall"
-        ],
-        "timestamps": [
-            0.0,
-            0.07999999821186066,
-            0.6800000071525574,
-            2.0,
-            5.320000171661377,
-            7.440000057220459,
-            7.960000038146973,
-            8.760000228881836
-        ]
-    },
     {
         "info": {
             "language": "en",
@@ -133,8 +133,8 @@
         },
         "segments": [
             {
-                "confidence": 0.9059738105990237,
-                "no_speech_confidence": 0.62060546875,
+                "confidence": 0.9063219732542974,
+                "no_speech_confidence": 0.6240234375,
                 "text": " Never gonna say goodbye Never gonna tell a lie and hurt you",
                 "time_interval": {
                     "end": 58.88,
@@ -154,8 +154,8 @@
         },
         "segments": [
             {
-                "confidence": 0.9059738105990237,
-                "no_speech_confidence": 0.62060546875,
+                "confidence": 0.9063219732542974,
+                "no_speech_confidence": 0.6240234375,
                 "text": " We've known each other for so long Your heart's been aching but you're too shy to say it",
                 "time_interval": {
                     "end": 68.88,
@@ -175,8 +175,8 @@
         },
         "segments": [
             {
-                "confidence": 0.9059738105990237,
-                "no_speech_confidence": 0.62060546875,
+                "confidence": 0.9063219732542974,
+                "no_speech_confidence": 0.6240234375,
                 "text": " Inside we both know what's been going on We know the game and we're gonna play it",
                 "time_interval": {
                     "end": 76.88,
@@ -196,7 +196,7 @@
         },
         "segments": [
             {
-                "confidence": 0.967252084465121,
+                "confidence": 0.9672820707485685,
                 "no_speech_confidence": 0.845703125,
                 "text": " And if you ask me how I'm feeling Don't tell me you're too blind to see",
                 "time_interval": {
@@ -217,7 +217,7 @@
         },
         "segments": [
             {
-                "confidence": 0.967252084465121,
+                "confidence": 0.9672820707485685,
                 "no_speech_confidence": 0.845703125,
                 "text": " Never gonna give you up Never gonna let you down",
                 "time_interval": {
@@ -238,7 +238,7 @@
         },
         "segments": [
             {
-                "confidence": 0.967252084465121,
+                "confidence": 0.9672820707485685,
                 "no_speech_confidence": 0.845703125,
                 "text": " Never gonna run around and desert you Never gonna make you cry",
                 "time_interval": {
@@ -259,7 +259,7 @@
         },
         "segments": [
             {
-                "confidence": 0.967252084465121,
+                "confidence": 0.9672820707485685,
                 "no_speech_confidence": 0.845703125,
                 "text": " Never gonna say goodbye Never gonna tell a lie and hurt you",
                 "time_interval": {
@@ -280,7 +280,7 @@
         },
         "segments": [
             {
-                "confidence": 0.9204295592681705,
+                "confidence": 0.9207292250767422,
                 "no_speech_confidence": 0.94921875,
                 "text": " Never gonna give you up Never gonna let you down",
                 "time_interval": {
@@ -301,7 +301,7 @@
         },
         "segments": [
             {
-                "confidence": 0.9204295592681705,
+                "confidence": 0.9207292250767422,
                 "no_speech_confidence": 0.94921875,
                 "text": " Never gonna run around and desert you Never gonna make you cry",
                 "time_interval": {
@@ -322,7 +322,7 @@
         },
         "segments": [
             {
-                "confidence": 0.9204295592681705,
+                "confidence": 0.9207292250767422,
                 "no_speech_confidence": 0.94921875,
                 "text": " Never gonna say goodbye Never gonna tell a lie and hurt you",
                 "time_interval": {
@@ -365,7 +365,7 @@
         },
         "segments": [
             {
-                "confidence": 0.8908876338811589,
+                "confidence": 0.8912798386547532,
                 "no_speech_confidence": 0.6396484375,
                 "text": " Never gonna give you up Never gonna give you up",
                 "time_interval": {
@@ -386,7 +386,7 @@
         },
         "segments": [
             {
-                "confidence": 0.8908876338811589,
+                "confidence": 0.8912798386547532,
                 "no_speech_confidence": 0.6396484375,
                 "text": " Never gonna give you up Never gonna give you up",
                 "time_interval": {
@@ -407,7 +407,7 @@
         },
         "segments": [
             {
-                "confidence": 0.8908876338811589,
+                "confidence": 0.8912798386547532,
                 "no_speech_confidence": 0.6396484375,
                 "text": " We've known each other for so long Your heart's been aching but you're too shy to say it",
                 "time_interval": {
@@ -428,7 +428,7 @@
         },
         "segments": [
             {
-                "confidence": 0.8908876338811589,
+                "confidence": 0.8912798386547532,
                 "no_speech_confidence": 0.6396484375,
                 "text": " Inside we both know what's been going on We know the game and we're gonna play it",
                 "time_interval": {
@@ -450,7 +450,7 @@
         "segments": [
             {
                 "confidence": 0.9688604363061694,
-                "no_speech_confidence": 0.72998046875,
+                "no_speech_confidence": 0.73291015625,
                 "text": " Your heart's been aching but you're too shy to say it",
                 "time_interval": {
                     "end": 144.88,
@@ -471,7 +471,7 @@
         "segments": [
             {
                 "confidence": 0.9688604363061694,
-                "no_speech_confidence": 0.72998046875,
+                "no_speech_confidence": 0.73291015625,
                 "text": " Inside we both know what's been going on We know the game and we're gonna play it",
                 "time_interval": {
                     "end": 152.88,
@@ -492,7 +492,7 @@
         "segments": [
             {
                 "confidence": 0.9688604363061694,
-                "no_speech_confidence": 0.72998046875,
+                "no_speech_confidence": 0.73291015625,
                 "text": " I just wanna tell you how I'm feeling Gotta make you understand",
                 "time_interval": {
                     "end": 160.88,
@@ -513,7 +513,7 @@
         "segments": [
             {
                 "confidence": 0.9688604363061694,
-                "no_speech_confidence": 0.72998046875,
+                "no_speech_confidence": 0.73291015625,
                 "text": " Never gonna give you up Never gonna let you down",
                 "time_interval": {
                     "end": 164.88,
@@ -526,6 +526,28 @@
             "text": " Never gonna give you up Never gonna let you down"
         }
     },
+    {
+        "captions": [
+            "a man in sunglasses and a blue shirt is walking",
+            "a young man wearing sunglasses and a blue shirt",
+            "a man wearing sunglasses and a blue shirt",
+            "a man in a blue jumpsuit and sunglasses walking by a fence",
+            "a young man wearing sunglasses and a blue shirt",
+            "the shadow of a person standing on the ground",
+            "a shadow of a person standing on a sidewalk",
+            "a man in a blue jumpsuit standing next to a fence"
+        ],
+        "timestamps": [
+            24.200000762939453,
+            24.520000457763672,
+            26.600000381469727,
+            27.799999237060547,
+            28.959999084472656,
+            30.440000534057617,
+            31.040000915527344,
+            32.0
+        ]
+    },
     {
         "info": {
             "language": "en",
@@ -533,8 +555,8 @@
         },
         "segments": [
             {
-                "confidence": 0.9625630656977605,
-                "no_speech_confidence": 0.89697265625,
+                "confidence": 0.9628652584161163,
+                "no_speech_confidence": 0.8984375,
                 "text": " Never gonna run around and desert you Never gonna make you cry",
                 "time_interval": {
                     "end": 170.88,
@@ -554,8 +576,8 @@
         },
         "segments": [
             {
-                "confidence": 0.9625630656977605,
-                "no_speech_confidence": 0.89697265625,
+                "confidence": 0.9628652584161163,
+                "no_speech_confidence": 0.8984375,
                 "text": " Never gonna say goodbye Never gonna tell a lie and hurt you",
                 "time_interval": {
                     "end": 176.88,
@@ -575,8 +597,8 @@
         },
         "segments": [
             {
-                "confidence": 0.9625630656977605,
-                "no_speech_confidence": 0.89697265625,
+                "confidence": 0.9628652584161163,
+                "no_speech_confidence": 0.8984375,
                 "text": " Never gonna give you up Never gonna let you down",
                 "time_interval": {
                     "end": 181.88,
@@ -596,8 +618,8 @@
         },
         "segments": [
             {
-                "confidence": 0.9625630656977605,
-                "no_speech_confidence": 0.89697265625,
+                "confidence": 0.9628652584161163,
+                "no_speech_confidence": 0.8984375,
                 "text": " Never gonna run around and desert you Never gonna make you cry",
                 "time_interval": {
                     "end": 187.88,
@@ -610,28 +632,6 @@
             "text": " Never gonna run around and desert you Never gonna make you cry"
         }
     },
-    {
-        "captions": [
-            "a man in sunglasses and a blue shirt is walking",
-            "a young man wearing sunglasses and a blue shirt",
-            "a man wearing sunglasses and a blue shirt",
-            "a man in a blue jumpsuit and sunglasses walking by a fence",
-            "a young man wearing sunglasses and a blue shirt",
-            "the shadow of a person standing on the ground",
-            "a shadow of a person standing on a sidewalk",
-            "a man in a blue jumpsuit standing next to a fence"
-        ],
-        "timestamps": [
-            24.200000762939453,
-            24.520000457763672,
-            26.600000381469727,
-            27.799999237060547,
-            28.959999084472656,
-            30.440000534057617,
-            31.040000915527344,
-            32.0
-        ]
-    },
     {
         "info": {
             "language": "en",
@@ -639,8 +639,8 @@
         },
         "segments": [
             {
-                "confidence": 0.9182383404568272,
-                "no_speech_confidence": 0.83544921875,
+                "confidence": 0.926492402808872,
+                "no_speech_confidence": 0.80859375,
                 "text": " Never gonna say goodbye Never gonna tell a lie and hurt you",
                 "time_interval": {
                     "end": 193.88,
@@ -660,8 +660,8 @@
         },
         "segments": [
             {
-                "confidence": 0.9182383404568272,
-                "no_speech_confidence": 0.83544921875,
+                "confidence": 0.926492402808872,
+                "no_speech_confidence": 0.80859375,
                 "text": " Never gonna give you up Never gonna let you down",
                 "time_interval": {
                     "end": 198.88,
@@ -681,8 +681,8 @@
         },
         "segments": [
             {
-                "confidence": 0.9182383404568272,
-                "no_speech_confidence": 0.83544921875,
+                "confidence": 0.926492402808872,
+                "no_speech_confidence": 0.80859375,
                 "text": " Never gonna run around and desert you Never gonna make you cry",
                 "time_interval": {
                     "end": 204.88,
@@ -702,8 +702,8 @@
         },
         "segments": [
             {
-                "confidence": 0.9182383404568272,
-                "no_speech_confidence": 0.83544921875,
+                "confidence": 0.926492402808872,
+                "no_speech_confidence": 0.80859375,
                 "text": " Never gonna say goodbye Never gonna tell a lie and hurt you",
                 "time_interval": {
                     "end": 210.88,
@@ -723,7 +723,7 @@
             "a man in a white jacket is singing",
             "a young man wearing sunglasses and a blue shirt",
             "a woman in a dress and sunglasses walking by a brick wall",
-            "a woman in a white dress and sunglasses is walking by a brick wall",
+            "a woman in a white dress and sunglasses is standing in front of a brick wall",
             "a woman with long blonde hair and sunglasses standing in front of a brick wall",
             "a man in sunglasses is standing next to a fence"
         ],
@@ -747,7 +747,7 @@
             "a man in a white shirt and tie standing behind a bar",
             "a man in a white shirt and suspenders sitting at a bar",
             "a man in a suit singing into a microphone",
-            "a woman with blonde hair standing in front of a wall"
+            "a woman in a black dress is dancing"
         ],
         "timestamps": [
             42.31999969482422,
@@ -787,7 +787,7 @@
             "three women are standing on chairs in front of a large window",
             "a man in suspenders holding a glass",
             "three women stand in front of a large window",
-            "david bowie - starman",
+            "a man in a suit is singing into a microphone",
             "a man in a white shirt is holding a glass",
             "a man standing in front of a wall with wine glasses",
             "a man in a suit is singing into a microphone",
@@ -960,16 +960,14 @@
     },
     {
         "captions": [
-            [
-                "a man is dancing in front of a brick wall",
-                "david bowie - the man who sold the world - david bowie stock videos & royalty-free footage",
-                "a man and woman are dancing on a stage",
-                "david bowie - starman - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie -",
-                "a man in a white shirt is standing next to a bar",
-                "three women in black outfits are dancing on a stage",
-                "a man in a striped shirt singing into a microphone",
-                "a man in a trench coat standing in an alley"
-            ]
+            "a man is dancing in front of a brick wall",
+            "david bowie - the man who sold the world - david bowie stock videos & royalty-free footage",
+            "a man and woman are dancing on a stage",
+            "david bowie - starman - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie - david bowie -",
+            "a man in a white shirt is standing next to a bar",
+            "three women in black outfits are dancing on a stage",
+            "a man in a striped shirt singing into a microphone",
+            "a man in a trench coat standing in an alley"
         ],
         "timestamps": [
             178.47999572753906,
@@ -1134,4 +1132,4 @@
         ],
         "transcription_id": 1
     }
-]
+]
\ No newline at end of file
diff --git a/aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_930699767cd541f2deb519f2f89b09d7.json b/aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_939a73622958d6746f38d629039ac1fe.json
similarity index 90%
rename from aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_930699767cd541f2deb519f2f89b09d7.json
rename to aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_939a73622958d6746f38d629039ac1fe.json
index 875b1a7b..401bba4f 100644
--- a/aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_930699767cd541f2deb519f2f89b09d7.json
+++ b/aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_939a73622958d6746f38d629039ac1fe.json
@@ -1,5 +1,15 @@
 [
     {
+        "captions": [
+            "a man is standing in front of a blackboard with a long stick",
+            "a man is standing on a stage in front of a classroom",
+            "a man holding a ball in front of a chalkboard",
+            "a man standing in front of a blackboard with a whiteboard",
+            "a man standing in front of a chalkboard with a ball",
+            "a black metal shelf mounted to the wall",
+            "a white ball is being thrown by a man",
+            "a black wall mounted camera is on a wall"
+        ],
         "timestamps": [
             0.0,
             11.133000373840332,
@@ -9,837 +19,827 @@
             67.53299713134766,
             69.80000305175781,
             72.26699829101562
-        ],
+        ]
+    },
+    {
         "captions": [
-            "a man is standing in front of a blackboard with a long stick",
-            "a man is standing on a stage in front of a classroom",
-            "a man holding a ball in front of a chalkboard",
-            "a man standing in front of a blackboard with a whiteboard",
-            "a man standing in front of a chalkboard with a ball",
-            "a black metal shelf mounted to the wall",
-            "a white ball is being thrown by a man",
-            "a black wall mounted camera is on a wall"
+            "a man standing in front of a blackboard with a calculator",
+            "a man is putting a piece of metal on a wall",
+            "a man is fixing a wall mounted television",
+            "a man standing in front of a blackboard with a man pointing",
+            "a group of students sitting in a lecture hall",
+            "a man is holding a ball in his hand",
+            "a man holding a white ball in his hands",
+            "a man holding a white ball in his hand"
+        ],
+        "timestamps": [
+            73.86699676513672,
+            89.86699676513672,
+            105.86699676513672,
+            121.86699676513672,
+            131.5330047607422,
+            133.66700744628906,
+            142.06700134277344,
+            158.06700134277344
         ]
     },
     {
-        "transcription": {
-            "text": " Now I want to return to the conservation of mechanical energy."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9155454257136106,
+                "no_speech_confidence": 0.006999969482421875,
                 "text": " Now I want to return to the conservation of mechanical energy.",
                 "time_interval": {
-                    "start": 0.0,
-                    "end": 6.0
+                    "end": 6.0,
+                    "start": 0.0
                 },
-                "confidence": 0.9155454257136106,
-                "no_speech_confidence": 0.006999969482421875,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Now I want to return to the conservation of mechanical energy."
         }
     },
     {
-        "transcription": {
-            "text": " I have here a pendulum."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9155454257136106,
+                "no_speech_confidence": 0.006999969482421875,
                 "text": " I have here a pendulum.",
                 "time_interval": {
-                    "start": 6.0,
-                    "end": 12.0
+                    "end": 12.0,
+                    "start": 6.0
                 },
-                "confidence": 0.9155454257136106,
-                "no_speech_confidence": 0.006999969482421875,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " I have here a pendulum."
         }
     },
     {
-        "transcription": {
-            "text": " I have an object that weighs 15 kilograms"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9155454257136106,
+                "no_speech_confidence": 0.006999969482421875,
                 "text": " I have an object that weighs 15 kilograms",
                 "time_interval": {
-                    "start": 12.0,
-                    "end": 18.0
+                    "end": 18.0,
+                    "start": 12.0
                 },
-                "confidence": 0.9155454257136106,
-                "no_speech_confidence": 0.006999969482421875,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " I have an object that weighs 15 kilograms"
         }
     },
     {
-        "transcription": {
-            "text": " and I can lift it up one meter, which I have done now."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9155454257136106,
+                "no_speech_confidence": 0.006999969482421875,
                 "text": " and I can lift it up one meter, which I have done now.",
                 "time_interval": {
-                    "start": 18.0,
-                    "end": 24.0
+                    "end": 24.0,
+                    "start": 18.0
                 },
-                "confidence": 0.9155454257136106,
-                "no_speech_confidence": 0.006999969482421875,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " and I can lift it up one meter, which I have done now."
         }
     },
     {
-        "timestamps": [
-            73.86699676513672,
-            89.86699676513672,
-            105.86699676513672,
-            121.86699676513672,
-            131.5330047607422,
-            133.66700744628906,
-            142.06700134277344,
-            158.06700134277344
-        ],
         "captions": [
-            "a man standing in front of a blackboard with a calculator",
-            "a man is putting a piece of metal on a wall",
-            "a man is fixing a wall mounted television",
-            "a man standing in front of a blackboard with a man pointing",
-            "a group of students sitting in a lecture hall",
-            "a man is holding a ball in his hand",
-            "a man holding a white ball in his hands",
-            "a man holding a white ball in his hand"
+            "a man holding a white ball in front of a wall",
+            "a group of people sitting in a lecture hall",
+            "a man holding a white ball in his hand",
+            "a lecture hall with a blackboard and people sitting in front of it",
+            "a man in a blue shirt leaning against a wall",
+            "a man in a blue shirt leaning against a wall",
+            "a group of people sitting in a lecture hall",
+            "a man in a blue shirt is talking to a crowd"
+        ],
+        "timestamps": [
+            174.06700134277344,
+            183.66700744628906,
+            185.4669952392578,
+            187.66700744628906,
+            191.33299255371094,
+            194.1999969482422,
+            200.4669952392578,
+            201.4669952392578
         ]
     },
     {
-        "transcription": {
-            "text": " If I let it fall, then that will be converted to kinetic energy."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8998440065155437,
+                "no_speech_confidence": 0.423828125,
                 "text": " If I let it fall, then that will be converted to kinetic energy.",
                 "time_interval": {
-                    "start": 24.0,
-                    "end": 30.0
+                    "end": 30.0,
+                    "start": 24.0
                 },
-                "confidence": 0.8998440065155437,
-                "no_speech_confidence": 0.423828125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " If I let it fall, then that will be converted to kinetic energy."
         }
     },
     {
-        "transcription": {
-            "text": " If I would let it swing from one meter height"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8998440065155437,
+                "no_speech_confidence": 0.423828125,
                 "text": " If I would let it swing from one meter height",
                 "time_interval": {
-                    "start": 30.0,
-                    "end": 36.0
+                    "end": 36.0,
+                    "start": 30.0
                 },
-                "confidence": 0.8998440065155437,
-                "no_speech_confidence": 0.423828125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " If I would let it swing from one meter height"
         }
     },
     {
-        "transcription": {
-            "text": " and you would be there and it would hit you, you'd be dead."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8998440065155437,
+                "no_speech_confidence": 0.423828125,
                 "text": " and you would be there and it would hit you, you'd be dead.",
                 "time_interval": {
-                    "start": 36.0,
-                    "end": 42.0
+                    "end": 42.0,
+                    "start": 36.0
                 },
-                "confidence": 0.8998440065155437,
-                "no_speech_confidence": 0.423828125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " and you would be there and it would hit you, you'd be dead."
         }
     },
     {
-        "transcription": {
-            "text": " 150 joules is enough to kill you."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8998440065155437,
+                "no_speech_confidence": 0.423828125,
                 "text": " 150 joules is enough to kill you.",
                 "time_interval": {
-                    "start": 42.0,
-                    "end": 48.0
+                    "end": 48.0,
+                    "start": 42.0
                 },
-                "confidence": 0.8998440065155437,
-                "no_speech_confidence": 0.423828125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " 150 joules is enough to kill you."
         }
     },
     {
-        "transcription": {
-            "text": " They use them to demolish buildings."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8811879148457943,
+                "no_speech_confidence": 0.59521484375,
                 "text": " They use them to demolish buildings.",
                 "time_interval": {
-                    "start": 48.0,
-                    "end": 54.0
+                    "end": 54.0,
+                    "start": 48.0
                 },
-                "confidence": 0.8811879148457943,
-                "no_speech_confidence": 0.59521484375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " They use them to demolish buildings."
         }
     },
     {
-        "transcription": {
-            "text": " You lift up a very heavy object, even heavier than this,"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8811879148457943,
+                "no_speech_confidence": 0.59521484375,
                 "text": " You lift up a very heavy object, even heavier than this,",
                 "time_interval": {
-                    "start": 54.0,
-                    "end": 60.0
+                    "end": 60.0,
+                    "start": 54.0
                 },
-                "confidence": 0.8811879148457943,
-                "no_speech_confidence": 0.59521484375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " You lift up a very heavy object, even heavier than this,"
         }
     },
     {
-        "transcription": {
-            "text": " and then you let it go, you swing it,"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8811879148457943,
+                "no_speech_confidence": 0.59521484375,
                 "text": " and then you let it go, you swing it,",
                 "time_interval": {
-                    "start": 60.0,
-                    "end": 66.0
+                    "end": 66.0,
+                    "start": 60.0
                 },
-                "confidence": 0.8811879148457943,
-                "no_speech_confidence": 0.59521484375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " and then you let it go, you swing it,"
         }
     },
     {
-        "transcription": {
-            "text": " thereby converting gravitational potential energy into kinetic energy"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8811879148457943,
+                "no_speech_confidence": 0.59521484375,
                 "text": " thereby converting gravitational potential energy into kinetic energy",
                 "time_interval": {
-                    "start": 66.0,
-                    "end": 72.0
+                    "end": 72.0,
+                    "start": 66.0
                 },
-                "confidence": 0.8811879148457943,
-                "no_speech_confidence": 0.59521484375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " thereby converting gravitational potential energy into kinetic energy"
         }
     },
     {
-        "timestamps": [
-            174.06700134277344,
-            183.66700744628906,
-            185.4669952392578,
-            187.66700744628906,
-            191.33299255371094,
-            194.1999969482422,
-            200.4669952392578,
-            201.4669952392578
-        ],
-        "captions": [
-            "a man holding a white ball in front of a wall",
-            "a group of people sitting in a lecture hall",
-            "a man holding a white ball in his hand",
-            "a lecture hall with a blackboard and people sitting in front of it",
-            "a man in a blue shirt leaning against a wall",
-            "a man in a blue shirt leaning against a wall",
-            "a group of people sitting in a lecture hall",
-            "a man in a blue shirt is talking to a crowd"
-        ]
-    },
-    {
-        "transcription": {
-            "text": " which is the whole idea of wrecking."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8715343445859605,
+                "no_speech_confidence": 0.40087890625,
                 "text": " which is the whole idea of wrecking.",
                 "time_interval": {
-                    "start": 72.0,
-                    "end": 78.0
+                    "end": 78.0,
+                    "start": 72.0
                 },
-                "confidence": 0.8715343445859605,
-                "no_speech_confidence": 0.40087890625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " which is the whole idea of wrecking."
         }
     },
     {
-        "transcription": {
-            "text": " So you are using then the conversion of gravitational potential energy to kinetic energy."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8715343445859605,
+                "no_speech_confidence": 0.40087890625,
                 "text": " So you are using then the conversion of gravitational potential energy to kinetic energy.",
                 "time_interval": {
-                    "start": 78.0,
-                    "end": 84.0
+                    "end": 84.0,
+                    "start": 78.0
                 },
-                "confidence": 0.8715343445859605,
-                "no_speech_confidence": 0.40087890625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " So you are using then the conversion of gravitational potential energy to kinetic energy."
         }
     },
     {
-        "transcription": {
-            "text": " Now, I am such a strong believer of the conservation of mechanical energy"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8715343445859605,
+                "no_speech_confidence": 0.40087890625,
                 "text": " Now, I am such a strong believer of the conservation of mechanical energy",
                 "time_interval": {
-                    "start": 84.0,
-                    "end": 90.0
+                    "end": 90.0,
+                    "start": 84.0
                 },
-                "confidence": 0.8715343445859605,
-                "no_speech_confidence": 0.40087890625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Now, I am such a strong believer of the conservation of mechanical energy"
         }
     },
     {
-        "transcription": {
-            "text": " that I am willing to put my life on the line."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8715343445859605,
+                "no_speech_confidence": 0.40087890625,
                 "text": " that I am willing to put my life on the line.",
                 "time_interval": {
-                    "start": 90.0,
-                    "end": 96.0
+                    "end": 96.0,
+                    "start": 90.0
                 },
-                "confidence": 0.8715343445859605,
-                "no_speech_confidence": 0.40087890625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " that I am willing to put my life on the line."
         }
     },
     {
-        "transcription": {
-            "text": " If I release that bob from a certain height,"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9383433771074657,
+                "no_speech_confidence": 0.01447296142578125,
                 "text": " If I release that bob from a certain height,",
                 "time_interval": {
-                    "start": 97.0,
-                    "end": 103.0
+                    "end": 103.0,
+                    "start": 97.0
                 },
-                "confidence": 0.9383433771074657,
-                "no_speech_confidence": 0.01447296142578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " If I release that bob from a certain height,"
         }
     },
     {
-        "transcription": {
-            "text": " then that bob can never come back to a point where the height is any larger."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9383433771074657,
+                "no_speech_confidence": 0.01447296142578125,
                 "text": " then that bob can never come back to a point where the height is any larger.",
                 "time_interval": {
-                    "start": 103.0,
-                    "end": 109.0
+                    "end": 109.0,
+                    "start": 103.0
                 },
-                "confidence": 0.9383433771074657,
-                "no_speech_confidence": 0.01447296142578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " then that bob can never come back to a point where the height is any larger."
         }
     },
     {
-        "transcription": {
-            "text": " If I release it from this height and it swings,"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9383433771074657,
+                "no_speech_confidence": 0.01447296142578125,
                 "text": " If I release it from this height and it swings,",
                 "time_interval": {
-                    "start": 111.0,
-                    "end": 117.0
+                    "end": 117.0,
+                    "start": 111.0
                 },
-                "confidence": 0.9383433771074657,
-                "no_speech_confidence": 0.01447296142578125,
                 "words": []
-            }
-        ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+            }
+        ],
+        "transcription": {
+            "text": " If I release it from this height and it swings,"
         }
     },
     {
-        "transcription": {
-            "text": " then when it reaches here, it could not be higher."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9383433771074657,
+                "no_speech_confidence": 0.01447296142578125,
                 "text": " then when it reaches here, it could not be higher.",
                 "time_interval": {
-                    "start": 117.0,
-                    "end": 121.0
+                    "end": 121.0,
+                    "start": 117.0
                 },
-                "confidence": 0.9383433771074657,
-                "no_speech_confidence": 0.01447296142578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " then when it reaches here, it could not be higher."
         }
     },
     {
-        "transcription": {
-            "text": " It could go from gravitational potential energy to kinetic energy"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8513452785243097,
+                "no_speech_confidence": 0.2396240234375,
                 "text": " It could go from gravitational potential energy to kinetic energy",
                 "time_interval": {
-                    "start": 121.0,
-                    "end": 127.0
+                    "end": 127.0,
+                    "start": 121.0
                 },
-                "confidence": 0.8513452785243097,
-                "no_speech_confidence": 0.2396240234375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " It could go from gravitational potential energy to kinetic energy"
         }
     },
     {
-        "transcription": {
-            "text": " back to gravitational potential energy and it will come to a stop here."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8513452785243097,
+                "no_speech_confidence": 0.2396240234375,
                 "text": " back to gravitational potential energy and it will come to a stop here.",
                 "time_interval": {
-                    "start": 127.0,
-                    "end": 133.0
+                    "end": 133.0,
+                    "start": 127.0
                 },
-                "confidence": 0.8513452785243097,
-                "no_speech_confidence": 0.2396240234375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " back to gravitational potential energy and it will come to a stop here."
         }
     },
     {
-        "transcription": {
-            "text": " And when it swings back, it should not be able to reach any higher"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8513452785243097,
+                "no_speech_confidence": 0.2396240234375,
                 "text": " And when it swings back, it should not be able to reach any higher",
                 "time_interval": {
-                    "start": 133.0,
-                    "end": 139.0
+                    "end": 139.0,
+                    "start": 133.0
                 },
-                "confidence": 0.8513452785243097,
-                "no_speech_confidence": 0.2396240234375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " And when it swings back, it should not be able to reach any higher"
         }
     },
     {
-        "transcription": {
-            "text": " provided that I do not give this object an initial speed when I stand here."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8513452785243097,
+                "no_speech_confidence": 0.2396240234375,
                 "text": " provided that I do not give this object an initial speed when I stand here.",
                 "time_interval": {
-                    "start": 139.0,
-                    "end": 145.0
+                    "end": 145.0,
+                    "start": 139.0
                 },
-                "confidence": 0.8513452785243097,
-                "no_speech_confidence": 0.2396240234375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " provided that I do not give this object an initial speed when I stand here."
         }
     },
     {
-        "transcription": {
-            "text": " I may not trust myself."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9217725291204704,
+                "no_speech_confidence": 0.0235748291015625,
                 "text": " I may not trust myself.",
                 "time_interval": {
-                    "start": 145.0,
-                    "end": 151.0
+                    "end": 151.0,
+                    "start": 145.0
                 },
-                "confidence": 0.9217725291204704,
-                "no_speech_confidence": 0.0235748291015625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " I may not trust myself."
         }
     },
     {
-        "transcription": {
-            "text": " I am going to release this object and I hope I will be able to do it at zero speed"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9217725291204704,
+                "no_speech_confidence": 0.0235748291015625,
                 "text": " I am going to release this object and I hope I will be able to do it at zero speed",
                 "time_interval": {
-                    "start": 151.0,
-                    "end": 157.0
+                    "end": 157.0,
+                    "start": 151.0
                 },
-                "confidence": 0.9217725291204704,
-                "no_speech_confidence": 0.0235748291015625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " I am going to release this object and I hope I will be able to do it at zero speed"
         }
     },
     {
-        "transcription": {
-            "text": " so that when it comes back it may touch my chin but it may not crush my chin."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9217725291204704,
+                "no_speech_confidence": 0.0235748291015625,
                 "text": " so that when it comes back it may touch my chin but it may not crush my chin.",
                 "time_interval": {
-                    "start": 157.0,
-                    "end": 163.0
+                    "end": 163.0,
+                    "start": 157.0
                 },
-                "confidence": 0.9217725291204704,
-                "no_speech_confidence": 0.0235748291015625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " so that when it comes back it may touch my chin but it may not crush my chin."
         }
     },
     {
-        "transcription": {
-            "text": " I want you to be extremely quiet because this is no joke."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9217725291204704,
+                "no_speech_confidence": 0.0235748291015625,
                 "text": " I want you to be extremely quiet because this is no joke.",
                 "time_interval": {
-                    "start": 163.0,
-                    "end": 169.0
+                    "end": 169.0,
+                    "start": 163.0
                 },
-                "confidence": 0.9217725291204704,
-                "no_speech_confidence": 0.0235748291015625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " I want you to be extremely quiet because this is no joke."
         }
     },
     {
-        "transcription": {
-            "text": " If I release this object at zero speed, then this will be my last lecture."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8646648422853658,
+                "no_speech_confidence": 0.429931640625,
                 "text": " If I release this object at zero speed, then this will be my last lecture.",
                 "time_interval": {
-                    "start": 169.0,
-                    "end": 175.0
+                    "end": 175.0,
+                    "start": 169.0
                 },
-                "confidence": 0.8646648422853658,
-                "no_speech_confidence": 0.429931640625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " If I release this object at zero speed, then this will be my last lecture."
         }
     },
     {
-        "transcription": {
-            "text": " I will close my eyes. I don't want to see this."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8646648422853658,
+                "no_speech_confidence": 0.429931640625,
                 "text": " I will close my eyes. I don't want to see this.",
                 "time_interval": {
-                    "start": 175.0,
-                    "end": 181.0
+                    "end": 181.0,
+                    "start": 175.0
                 },
-                "confidence": 0.8646648422853658,
-                "no_speech_confidence": 0.429931640625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " I will close my eyes. I don't want to see this."
         }
     },
     {
-        "transcription": {
-            "text": " So please be very quiet. I almost didn't sleep all night."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8646648422853658,
+                "no_speech_confidence": 0.429931640625,
                 "text": " So please be very quiet. I almost didn't sleep all night.",
                 "time_interval": {
-                    "start": 181.0,
-                    "end": 187.0
+                    "end": 187.0,
+                    "start": 181.0
                 },
-                "confidence": 0.8646648422853658,
-                "no_speech_confidence": 0.429931640625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " So please be very quiet. I almost didn't sleep all night."
         }
     },
     {
-        "transcription": {
-            "text": " Three, two, one, zero."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8646648422853658,
+                "no_speech_confidence": 0.429931640625,
                 "text": " Three, two, one, zero.",
                 "time_interval": {
-                    "start": 187.0,
-                    "end": 193.0
+                    "end": 193.0,
+                    "start": 187.0
                 },
-                "confidence": 0.8646648422853658,
-                "no_speech_confidence": 0.429931640625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Three, two, one, zero."
         }
     },
     {
-        "transcription": {
-            "text": " Physics works and I am still alive."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8780664047938203,
+                "no_speech_confidence": 0.07843017578125,
                 "text": " Physics works and I am still alive.",
                 "time_interval": {
-                    "start": 199.0,
-                    "end": 205.0
+                    "end": 205.0,
+                    "start": 199.0
                 },
-                "confidence": 0.8780664047938203,
-                "no_speech_confidence": 0.07843017578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Physics works and I am still alive."
         }
     },
     {
-        "transcription": {
-            "text": " Physics works and I am still alive."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8780664047938203,
+                "no_speech_confidence": 0.07843017578125,
                 "text": " Physics works and I am still alive.",
                 "time_interval": {
-                    "start": 205.0,
-                    "end": 211.0
+                    "end": 211.0,
+                    "start": 205.0
                 },
-                "confidence": 0.8780664047938203,
-                "no_speech_confidence": 0.07843017578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Physics works and I am still alive."
         }
     },
     {
-        "transcription": {
-            "text": " Physics works and I am still alive."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8780664047938203,
+                "no_speech_confidence": 0.07843017578125,
                 "text": " Physics works and I am still alive.",
                 "time_interval": {
-                    "start": 211.0,
-                    "end": 217.0
+                    "end": 217.0,
+                    "start": 211.0
                 },
-                "confidence": 0.8780664047938203,
-                "no_speech_confidence": 0.07843017578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Physics works and I am still alive."
         }
     },
     {
-        "transcription": {
-            "text": " Physics works and I am still alive."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8780664047938203,
+                "no_speech_confidence": 0.07843017578125,
                 "text": " Physics works and I am still alive.",
                 "time_interval": {
-                    "start": 217.0,
-                    "end": 223.0
+                    "end": 223.0,
+                    "start": 217.0
                 },
-                "confidence": 0.8780664047938203,
-                "no_speech_confidence": 0.07843017578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Physics works and I am still alive."
         }
     },
     {
-        "transcription": {
-            "text": " Physics works and I am still alive."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8780664047938203,
+                "no_speech_confidence": 0.07843017578125,
                 "text": " Physics works and I am still alive.",
                 "time_interval": {
-                    "start": 223.0,
-                    "end": 227.0
+                    "end": 227.0,
+                    "start": 223.0
                 },
-                "confidence": 0.8780664047938203,
-                "no_speech_confidence": 0.07843017578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Physics works and I am still alive."
         }
     },
     {
diff --git a/aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_5b4f9056476e687ed36db34a7e82fa26.json b/aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_d08b7811a5fe2a0c163391057ba24199.json
similarity index 90%
rename from aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_5b4f9056476e687ed36db34a7e82fa26.json
rename to aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_d08b7811a5fe2a0c163391057ba24199.json
index 526866f5..c82334a7 100644
--- a/aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_5b4f9056476e687ed36db34a7e82fa26.json
+++ b/aana/tests/files/expected/endpoints/chat_with_video/video_index_stream_d08b7811a5fe2a0c163391057ba24199.json
@@ -2,12 +2,12 @@
     {
         "info": {
             "language": "en",
-            "language_confidence": 0.361572265625
+            "language_confidence": 0.360107421875
         },
         "segments": [
             {
                 "confidence": 0.6431313717877822,
-                "no_speech_confidence": 0.93408203125,
+                "no_speech_confidence": 0.9345703125,
                 "text": " you",
                 "time_interval": {
                     "end": 2.06,
diff --git a/aana/tests/files/expected/endpoints/chat_with_video/video_metadata_0298f701c7becbf0aaa913d774c4d1b1.json b/aana/tests/files/expected/endpoints/chat_with_video/video_metadata_0298f701c7becbf0aaa913d774c4d1b1.json
index 4432ea9e..7b5245c8 100644
--- a/aana/tests/files/expected/endpoints/chat_with_video/video_metadata_0298f701c7becbf0aaa913d774c4d1b1.json
+++ b/aana/tests/files/expected/endpoints/chat_with_video/video_metadata_0298f701c7becbf0aaa913d774c4d1b1.json
@@ -1,28 +1,28 @@
 {
-    "metadata": {
-        "title": "Rick Astley - Never Gonna Give You Up (Official Music Video)",
-        "description": "The official video for \u201cNever Gonna Give You Up\u201d by Rick Astley. \n\nThe new album 'Are We There Yet?' is out now: Download here: https://RickAstley.lnk.to/AreWeThereYetFA/itunes\n\n\u201cNever Gonna Give You Up\u201d was a global smash on its release in July 1987, topping the charts in 25 countries including Rick\u2019s native UK and the US Billboard Hot 100.  It also won the Brit Award for Best single in 1988. Stock Aitken and Waterman wrote and produced the track which was the lead-off single and lead track from Rick\u2019s debut LP \u201cWhenever You Need Somebody\u201d.  The album was itself a UK number one and would go on to sell over 15 million copies worldwide.\n\nThe legendary video was directed by Simon West \u2013 who later went on to make Hollywood blockbusters such as Con Air, Lara Croft \u2013 Tomb Raider and The Expendables 2.  The video passed the 1bn YouTube views milestone on 28 July 2021.\n\nSubscribe to the official Rick Astley YouTube channel: https://RickAstley.lnk.to/YTSubID\n\nFollow Rick Astley:\nFacebook: https://RickAstley.lnk.to/FBFollowID \nTwitter: https://RickAstley.lnk.to/TwitterID \nInstagram: https://RickAstley.lnk.to/InstagramID \nWebsite: https://RickAstley.lnk.to/storeID \nTikTok: https://RickAstley.lnk.to/TikTokID\n\nListen to Rick Astley:\nSpotify: https://RickAstley.lnk.to/SpotifyID \nApple Music: https://RickAstley.lnk.to/AppleMusicID \nAmazon Music: https://RickAstley.lnk.to/AmazonMusicID \nDeezer: https://RickAstley.lnk.to/DeezerID \n\nLyrics:\nWe\u2019re no strangers to love\nYou know the rules and so do I\nA full commitment\u2019s what I\u2019m thinking of\nYou wouldn\u2019t get this from any other guy\n\nI just wanna tell you how I\u2019m feeling\nGotta make you understand\n\nNever gonna give you up\nNever gonna let you down\nNever gonna run around and desert you\nNever gonna make you cry\nNever gonna say goodbye\nNever gonna tell a lie and hurt you\n\nWe\u2019ve known each other for so long\nYour heart\u2019s been aching but you\u2019re too shy to say it\nInside we both know what\u2019s been going on\nWe know the game and we\u2019re gonna play it\n\nAnd if you ask me how I\u2019m feeling\nDon\u2019t tell me you\u2019re too blind to see\n\nNever gonna give you up\nNever gonna let you down\nNever gonna run around and desert you\nNever gonna make you cry\nNever gonna say goodbye\nNever gonna tell a lie and hurt you\n\n#RickAstley #NeverGonnaGiveYouUp #WheneverYouNeedSomebody #OfficialMusicVideo"
-    },
     "execution_time": {
-        "sampling_params": 0,
-        "video_params": 0,
-        "whisper_params": 0,
-        "video": 0,
+        "delete_media": 0,
         "download_video": 0,
+        "generate_combined_timeline": 0,
+        "generate_dialog": 0,
         "generate_frames_for_video": 0,
         "hf_blip2_opt_2_7b_video": 0,
-        "whisper_medium_transcribe_video": 0,
+        "load_video_captions_hf_blip2_opt_2_7b": 0,
+        "load_video_metadata": 0.0026950836181640625,
+        "load_video_transcription": 0,
         "media_id": 0,
         "question": 0,
-        "load_video_metadata": 0.0021810531616210938,
-        "load_video_transcription": 0,
-        "load_video_captions_hf_blip2_opt_2_7b": 0,
-        "generate_combined_timeline": 0,
-        "generate_dialog": 0,
-        "vllm_llama2_7b_chat_dialog_stream_video": 0,
+        "sampling_params": 0,
         "save_video": 0,
-        "delete_media": 0,
+        "save_video_captions_hf_blip2_opt_2_7b": 0,
         "save_video_transcription": 0,
-        "save_video_captions_hf_blip2_opt_2_7b": 0
+        "video": 0,
+        "video_params": 0,
+        "vllm_llama2_7b_chat_dialog_stream_video": 0,
+        "whisper_medium_transcribe_video": 0,
+        "whisper_params": 0
+    },
+    "metadata": {
+        "description": "The official video for \u201cNever Gonna Give You Up\u201d by Rick Astley. \n\nThe new album 'Are We There Yet?' is out now: Download here: https://RickAstley.lnk.to/AreWeThereYetFA/itunes\n\n\u201cNever Gonna Give You Up\u201d was a global smash on its release in July 1987, topping the charts in 25 countries including Rick\u2019s native UK and the US Billboard Hot 100.  It also won the Brit Award for Best single in 1988. Stock Aitken and Waterman wrote and produced the track which was the lead-off single and lead track from Rick\u2019s debut LP \u201cWhenever You Need Somebody\u201d.  The album was itself a UK number one and would go on to sell over 15 million copies worldwide.\n\nThe legendary video was directed by Simon West \u2013 who later went on to make Hollywood blockbusters such as Con Air, Lara Croft \u2013 Tomb Raider and The Expendables 2.  The video passed the 1bn YouTube views milestone on 28 July 2021.\n\nSubscribe to the official Rick Astley YouTube channel: https://RickAstley.lnk.to/YTSubID\n\nFollow Rick Astley:\nFacebook: https://RickAstley.lnk.to/FBFollowID \nTwitter: https://RickAstley.lnk.to/TwitterID \nInstagram: https://RickAstley.lnk.to/InstagramID \nWebsite: https://RickAstley.lnk.to/storeID \nTikTok: https://RickAstley.lnk.to/TikTokID\n\nListen to Rick Astley:\nSpotify: https://RickAstley.lnk.to/SpotifyID \nApple Music: https://RickAstley.lnk.to/AppleMusicID \nAmazon Music: https://RickAstley.lnk.to/AmazonMusicID \nDeezer: https://RickAstley.lnk.to/DeezerID \n\nLyrics:\nWe\u2019re no strangers to love\nYou know the rules and so do I\nA full commitment\u2019s what I\u2019m thinking of\nYou wouldn\u2019t get this from any other guy\n\nI just wanna tell you how I\u2019m feeling\nGotta make you understand\n\nNever gonna give you up\nNever gonna let you down\nNever gonna run around and desert you\nNever gonna make you cry\nNever gonna say goodbye\nNever gonna tell a lie and hurt you\n\nWe\u2019ve known each other for so long\nYour heart\u2019s been aching but you\u2019re too shy to say it\nInside we both know what\u2019s been going on\nWe know the game and we\u2019re gonna play it\n\nAnd if you ask me how I\u2019m feeling\nDon\u2019t tell me you\u2019re too blind to see\n\nNever gonna give you up\nNever gonna let you down\nNever gonna run around and desert you\nNever gonna make you cry\nNever gonna say goodbye\nNever gonna tell a lie and hurt you\n\n#RickAstley #NeverGonnaGiveYouUp #WheneverYouNeedSomebody #OfficialMusicVideo",
+        "title": "Rick Astley - Never Gonna Give You Up (Official Music Video)"
     }
 }
\ No newline at end of file
diff --git a/aana/tests/files/expected/endpoints/chat_with_video/video_metadata_5db7acfad27a2ce9c55fd9d4f4ca61e8.json b/aana/tests/files/expected/endpoints/chat_with_video/video_metadata_5db7acfad27a2ce9c55fd9d4f4ca61e8.json
index bf8a71da..d0c194e2 100644
--- a/aana/tests/files/expected/endpoints/chat_with_video/video_metadata_5db7acfad27a2ce9c55fd9d4f4ca61e8.json
+++ b/aana/tests/files/expected/endpoints/chat_with_video/video_metadata_5db7acfad27a2ce9c55fd9d4f4ca61e8.json
@@ -1,28 +1,28 @@
 {
-    "metadata": {
-        "title": "",
-        "description": ""
-    },
     "execution_time": {
-        "sampling_params": 0,
-        "video_params": 0,
-        "whisper_params": 0,
-        "video": 0,
+        "delete_media": 0,
         "download_video": 0,
+        "generate_combined_timeline": 0,
+        "generate_dialog": 0,
         "generate_frames_for_video": 0,
         "hf_blip2_opt_2_7b_video": 0,
-        "whisper_medium_transcribe_video": 0,
+        "load_video_captions_hf_blip2_opt_2_7b": 0,
+        "load_video_metadata": 0.002285003662109375,
+        "load_video_transcription": 0,
         "media_id": 0,
         "question": 0,
-        "load_video_metadata": 0.001256704330444336,
-        "load_video_transcription": 0,
-        "load_video_captions_hf_blip2_opt_2_7b": 0,
-        "generate_combined_timeline": 0,
-        "generate_dialog": 0,
-        "vllm_llama2_7b_chat_dialog_stream_video": 0,
+        "sampling_params": 0,
         "save_video": 0,
-        "delete_media": 0,
+        "save_video_captions_hf_blip2_opt_2_7b": 0,
         "save_video_transcription": 0,
-        "save_video_captions_hf_blip2_opt_2_7b": 0
+        "video": 0,
+        "video_params": 0,
+        "vllm_llama2_7b_chat_dialog_stream_video": 0,
+        "whisper_medium_transcribe_video": 0,
+        "whisper_params": 0
+    },
+    "metadata": {
+        "description": "",
+        "title": ""
     }
 }
\ No newline at end of file
diff --git a/aana/tests/files/expected/endpoints/chat_with_video/video_metadata_bc75d9036fa2e8e85a79cd23c3162de7.json b/aana/tests/files/expected/endpoints/chat_with_video/video_metadata_bc75d9036fa2e8e85a79cd23c3162de7.json
index 5935813d..aa5eacd5 100644
--- a/aana/tests/files/expected/endpoints/chat_with_video/video_metadata_bc75d9036fa2e8e85a79cd23c3162de7.json
+++ b/aana/tests/files/expected/endpoints/chat_with_video/video_metadata_bc75d9036fa2e8e85a79cd23c3162de7.json
@@ -7,7 +7,7 @@
         "generate_frames_for_video": 0,
         "hf_blip2_opt_2_7b_video": 0,
         "load_video_captions_hf_blip2_opt_2_7b": 0,
-        "load_video_metadata": 0.0021924972534179688,
+        "load_video_metadata": 0.002431154251098633,
         "load_video_transcription": 0,
         "media_id": 0,
         "question": 0,
diff --git a/aana/tests/files/expected/endpoints/whisper/video_get_transcription_5db7acfad27a2ce9c55fd9d4f4ca61e8.json b/aana/tests/files/expected/endpoints/whisper/video_get_transcription_5db7acfad27a2ce9c55fd9d4f4ca61e8.json
index 790913aa..00de3a2c 100644
--- a/aana/tests/files/expected/endpoints/whisper/video_get_transcription_5db7acfad27a2ce9c55fd9d4f4ca61e8.json
+++ b/aana/tests/files/expected/endpoints/whisper/video_get_transcription_5db7acfad27a2ce9c55fd9d4f4ca61e8.json
@@ -1,392 +1,392 @@
 {
-    "transcription": {
-        "text": " Now I want to return to the conservation of mechanical energy.\n I have here a pendulum.\n I have an object that weighs 15 kilograms\n and I can lift it up one meter, which I have done now.\n If I let it fall, then that will be converted to kinetic energy.\n If I would let it swing from one meter height\n and you would be there and it would hit you, you'd be dead.\n 150 joules is enough to kill you.\n They use them to demolish buildings.\n You lift up a very heavy object, even heavier than this,\n and then you let it go, you swing it,\n thereby converting gravitational potential energy into kinetic energy\n which is the whole idea of wrecking.\n So you are using then the conversion of gravitational potential energy to kinetic energy.\n Now, I am such a strong believer of the conservation of mechanical energy\n that I am willing to put my life on the line.\n If I release that bob from a certain height,\n then that bob can never come back to a point where the height is any larger.\n If I release it from this height and it swings,\n then when it reaches here, it could not be higher.\n It could go from gravitational potential energy to kinetic energy\n back to gravitational potential energy and it will come to a stop here.\n And when it swings back, it should not be able to reach any higher\n provided that I do not give this object an initial speed when I stand here.\n I may not trust myself.\n I am going to release this object and I hope I will be able to do it at zero speed\n so that when it comes back it may touch my chin but it may not crush my chin.\n I want you to be extremely quiet because this is no joke.\n If I release this object at zero speed, then this will be my last lecture.\n I will close my eyes. I don't want to see this.\n So please be very quiet. I almost didn't sleep all night.\n Three, two, one, zero.\n Physics works and I am still alive.\n Physics works and I am still alive.\n Physics works and I am still alive.\n Physics works and I am still alive.\n Physics works and I am still alive."
+    "execution_time": {
+        "delete_media": 0,
+        "download_video": 0,
+        "load_video_transcription": 0.006000041961669922,
+        "media_id": 0,
+        "save_video": 0,
+        "save_video_transcription": 0,
+        "video": 0,
+        "whisper_medium_transcribe_video": 0,
+        "whisper_params": 0
+    },
+    "info": {
+        "language": "en",
+        "language_confidence": 0.982421875
     },
     "segments": [
         {
+            "confidence": 0.9155454257136106,
+            "no_speech_confidence": 0.006999969482421875,
             "text": " Now I want to return to the conservation of mechanical energy.",
             "time_interval": {
-                "start": 0.0,
-                "end": 6.0
+                "end": 6.0,
+                "start": 0.0
             },
-            "confidence": 0.9155454257136106,
-            "no_speech_confidence": 0.006999969482421875,
             "words": []
         },
         {
+            "confidence": 0.9155454257136106,
+            "no_speech_confidence": 0.006999969482421875,
             "text": " I have here a pendulum.",
             "time_interval": {
-                "start": 6.0,
-                "end": 12.0
+                "end": 12.0,
+                "start": 6.0
             },
-            "confidence": 0.9155454257136106,
-            "no_speech_confidence": 0.006999969482421875,
             "words": []
         },
         {
+            "confidence": 0.9155454257136106,
+            "no_speech_confidence": 0.006999969482421875,
             "text": " I have an object that weighs 15 kilograms",
             "time_interval": {
-                "start": 12.0,
-                "end": 18.0
+                "end": 18.0,
+                "start": 12.0
             },
-            "confidence": 0.9155454257136106,
-            "no_speech_confidence": 0.006999969482421875,
             "words": []
         },
         {
+            "confidence": 0.9155454257136106,
+            "no_speech_confidence": 0.006999969482421875,
             "text": " and I can lift it up one meter, which I have done now.",
             "time_interval": {
-                "start": 18.0,
-                "end": 24.0
+                "end": 24.0,
+                "start": 18.0
             },
-            "confidence": 0.9155454257136106,
-            "no_speech_confidence": 0.006999969482421875,
             "words": []
         },
         {
+            "confidence": 0.8998440065155437,
+            "no_speech_confidence": 0.423828125,
             "text": " If I let it fall, then that will be converted to kinetic energy.",
             "time_interval": {
-                "start": 24.0,
-                "end": 30.0
+                "end": 30.0,
+                "start": 24.0
             },
-            "confidence": 0.8998440065155437,
-            "no_speech_confidence": 0.423828125,
             "words": []
         },
         {
+            "confidence": 0.8998440065155437,
+            "no_speech_confidence": 0.423828125,
             "text": " If I would let it swing from one meter height",
             "time_interval": {
-                "start": 30.0,
-                "end": 36.0
+                "end": 36.0,
+                "start": 30.0
             },
-            "confidence": 0.8998440065155437,
-            "no_speech_confidence": 0.423828125,
             "words": []
         },
         {
+            "confidence": 0.8998440065155437,
+            "no_speech_confidence": 0.423828125,
             "text": " and you would be there and it would hit you, you'd be dead.",
             "time_interval": {
-                "start": 36.0,
-                "end": 42.0
+                "end": 42.0,
+                "start": 36.0
             },
-            "confidence": 0.8998440065155437,
-            "no_speech_confidence": 0.423828125,
             "words": []
         },
         {
+            "confidence": 0.8998440065155437,
+            "no_speech_confidence": 0.423828125,
             "text": " 150 joules is enough to kill you.",
             "time_interval": {
-                "start": 42.0,
-                "end": 48.0
+                "end": 48.0,
+                "start": 42.0
             },
-            "confidence": 0.8998440065155437,
-            "no_speech_confidence": 0.423828125,
             "words": []
         },
         {
+            "confidence": 0.8811879148457943,
+            "no_speech_confidence": 0.59521484375,
             "text": " They use them to demolish buildings.",
             "time_interval": {
-                "start": 48.0,
-                "end": 54.0
+                "end": 54.0,
+                "start": 48.0
             },
-            "confidence": 0.8811879148457943,
-            "no_speech_confidence": 0.59521484375,
             "words": []
         },
         {
+            "confidence": 0.8811879148457943,
+            "no_speech_confidence": 0.59521484375,
             "text": " You lift up a very heavy object, even heavier than this,",
             "time_interval": {
-                "start": 54.0,
-                "end": 60.0
+                "end": 60.0,
+                "start": 54.0
             },
-            "confidence": 0.8811879148457943,
-            "no_speech_confidence": 0.59521484375,
             "words": []
         },
         {
+            "confidence": 0.8811879148457943,
+            "no_speech_confidence": 0.59521484375,
             "text": " and then you let it go, you swing it,",
             "time_interval": {
-                "start": 60.0,
-                "end": 66.0
+                "end": 66.0,
+                "start": 60.0
             },
-            "confidence": 0.8811879148457943,
-            "no_speech_confidence": 0.59521484375,
             "words": []
         },
         {
+            "confidence": 0.8811879148457943,
+            "no_speech_confidence": 0.59521484375,
             "text": " thereby converting gravitational potential energy into kinetic energy",
             "time_interval": {
-                "start": 66.0,
-                "end": 72.0
+                "end": 72.0,
+                "start": 66.0
             },
-            "confidence": 0.8811879148457943,
-            "no_speech_confidence": 0.59521484375,
             "words": []
         },
         {
+            "confidence": 0.8715343445859605,
+            "no_speech_confidence": 0.40087890625,
             "text": " which is the whole idea of wrecking.",
             "time_interval": {
-                "start": 72.0,
-                "end": 78.0
+                "end": 78.0,
+                "start": 72.0
             },
-            "confidence": 0.8715343445859605,
-            "no_speech_confidence": 0.40087890625,
             "words": []
         },
         {
+            "confidence": 0.8715343445859605,
+            "no_speech_confidence": 0.40087890625,
             "text": " So you are using then the conversion of gravitational potential energy to kinetic energy.",
             "time_interval": {
-                "start": 78.0,
-                "end": 84.0
+                "end": 84.0,
+                "start": 78.0
             },
-            "confidence": 0.8715343445859605,
-            "no_speech_confidence": 0.40087890625,
             "words": []
         },
         {
+            "confidence": 0.8715343445859605,
+            "no_speech_confidence": 0.40087890625,
             "text": " Now, I am such a strong believer of the conservation of mechanical energy",
             "time_interval": {
-                "start": 84.0,
-                "end": 90.0
+                "end": 90.0,
+                "start": 84.0
             },
-            "confidence": 0.8715343445859605,
-            "no_speech_confidence": 0.40087890625,
             "words": []
         },
         {
+            "confidence": 0.8715343445859605,
+            "no_speech_confidence": 0.40087890625,
             "text": " that I am willing to put my life on the line.",
             "time_interval": {
-                "start": 90.0,
-                "end": 96.0
+                "end": 96.0,
+                "start": 90.0
             },
-            "confidence": 0.8715343445859605,
-            "no_speech_confidence": 0.40087890625,
             "words": []
         },
         {
+            "confidence": 0.9383433771074657,
+            "no_speech_confidence": 0.01447296142578125,
             "text": " If I release that bob from a certain height,",
             "time_interval": {
-                "start": 97.0,
-                "end": 103.0
+                "end": 103.0,
+                "start": 97.0
             },
-            "confidence": 0.9383433771074657,
-            "no_speech_confidence": 0.01447296142578125,
             "words": []
         },
         {
+            "confidence": 0.9383433771074657,
+            "no_speech_confidence": 0.01447296142578125,
             "text": " then that bob can never come back to a point where the height is any larger.",
             "time_interval": {
-                "start": 103.0,
-                "end": 109.0
+                "end": 109.0,
+                "start": 103.0
             },
-            "confidence": 0.9383433771074657,
-            "no_speech_confidence": 0.01447296142578125,
             "words": []
         },
         {
+            "confidence": 0.9383433771074657,
+            "no_speech_confidence": 0.01447296142578125,
             "text": " If I release it from this height and it swings,",
             "time_interval": {
-                "start": 111.0,
-                "end": 117.0
+                "end": 117.0,
+                "start": 111.0
             },
-            "confidence": 0.9383433771074657,
-            "no_speech_confidence": 0.01447296142578125,
             "words": []
         },
         {
+            "confidence": 0.9383433771074657,
+            "no_speech_confidence": 0.01447296142578125,
             "text": " then when it reaches here, it could not be higher.",
             "time_interval": {
-                "start": 117.0,
-                "end": 121.0
+                "end": 121.0,
+                "start": 117.0
             },
-            "confidence": 0.9383433771074657,
-            "no_speech_confidence": 0.01447296142578125,
             "words": []
         },
         {
+            "confidence": 0.8513452785243097,
+            "no_speech_confidence": 0.2396240234375,
             "text": " It could go from gravitational potential energy to kinetic energy",
             "time_interval": {
-                "start": 121.0,
-                "end": 127.0
+                "end": 127.0,
+                "start": 121.0
             },
-            "confidence": 0.8513452785243097,
-            "no_speech_confidence": 0.2396240234375,
             "words": []
         },
         {
+            "confidence": 0.8513452785243097,
+            "no_speech_confidence": 0.2396240234375,
             "text": " back to gravitational potential energy and it will come to a stop here.",
             "time_interval": {
-                "start": 127.0,
-                "end": 133.0
+                "end": 133.0,
+                "start": 127.0
             },
-            "confidence": 0.8513452785243097,
-            "no_speech_confidence": 0.2396240234375,
             "words": []
         },
         {
+            "confidence": 0.8513452785243097,
+            "no_speech_confidence": 0.2396240234375,
             "text": " And when it swings back, it should not be able to reach any higher",
             "time_interval": {
-                "start": 133.0,
-                "end": 139.0
+                "end": 139.0,
+                "start": 133.0
             },
-            "confidence": 0.8513452785243097,
-            "no_speech_confidence": 0.2396240234375,
             "words": []
         },
         {
+            "confidence": 0.8513452785243097,
+            "no_speech_confidence": 0.2396240234375,
             "text": " provided that I do not give this object an initial speed when I stand here.",
             "time_interval": {
-                "start": 139.0,
-                "end": 145.0
+                "end": 145.0,
+                "start": 139.0
             },
-            "confidence": 0.8513452785243097,
-            "no_speech_confidence": 0.2396240234375,
             "words": []
         },
         {
+            "confidence": 0.9217725291204704,
+            "no_speech_confidence": 0.0235748291015625,
             "text": " I may not trust myself.",
             "time_interval": {
-                "start": 145.0,
-                "end": 151.0
+                "end": 151.0,
+                "start": 145.0
             },
-            "confidence": 0.9217725291204704,
-            "no_speech_confidence": 0.0235748291015625,
             "words": []
         },
         {
+            "confidence": 0.9217725291204704,
+            "no_speech_confidence": 0.0235748291015625,
             "text": " I am going to release this object and I hope I will be able to do it at zero speed",
             "time_interval": {
-                "start": 151.0,
-                "end": 157.0
+                "end": 157.0,
+                "start": 151.0
             },
-            "confidence": 0.9217725291204704,
-            "no_speech_confidence": 0.0235748291015625,
             "words": []
         },
         {
+            "confidence": 0.9217725291204704,
+            "no_speech_confidence": 0.0235748291015625,
             "text": " so that when it comes back it may touch my chin but it may not crush my chin.",
             "time_interval": {
-                "start": 157.0,
-                "end": 163.0
+                "end": 163.0,
+                "start": 157.0
             },
-            "confidence": 0.9217725291204704,
-            "no_speech_confidence": 0.0235748291015625,
             "words": []
         },
         {
+            "confidence": 0.9217725291204704,
+            "no_speech_confidence": 0.0235748291015625,
             "text": " I want you to be extremely quiet because this is no joke.",
             "time_interval": {
-                "start": 163.0,
-                "end": 169.0
+                "end": 169.0,
+                "start": 163.0
             },
-            "confidence": 0.9217725291204704,
-            "no_speech_confidence": 0.0235748291015625,
             "words": []
         },
         {
+            "confidence": 0.8646648422853658,
+            "no_speech_confidence": 0.429931640625,
             "text": " If I release this object at zero speed, then this will be my last lecture.",
             "time_interval": {
-                "start": 169.0,
-                "end": 175.0
+                "end": 175.0,
+                "start": 169.0
             },
-            "confidence": 0.8646648422853658,
-            "no_speech_confidence": 0.429931640625,
             "words": []
         },
         {
+            "confidence": 0.8646648422853658,
+            "no_speech_confidence": 0.429931640625,
             "text": " I will close my eyes. I don't want to see this.",
             "time_interval": {
-                "start": 175.0,
-                "end": 181.0
+                "end": 181.0,
+                "start": 175.0
             },
-            "confidence": 0.8646648422853658,
-            "no_speech_confidence": 0.429931640625,
             "words": []
         },
         {
+            "confidence": 0.8646648422853658,
+            "no_speech_confidence": 0.429931640625,
             "text": " So please be very quiet. I almost didn't sleep all night.",
             "time_interval": {
-                "start": 181.0,
-                "end": 187.0
+                "end": 187.0,
+                "start": 181.0
             },
-            "confidence": 0.8646648422853658,
-            "no_speech_confidence": 0.429931640625,
             "words": []
         },
         {
+            "confidence": 0.8646648422853658,
+            "no_speech_confidence": 0.429931640625,
             "text": " Three, two, one, zero.",
             "time_interval": {
-                "start": 187.0,
-                "end": 193.0
+                "end": 193.0,
+                "start": 187.0
             },
-            "confidence": 0.8646648422853658,
-            "no_speech_confidence": 0.429931640625,
             "words": []
         },
         {
+            "confidence": 0.8780664047938203,
+            "no_speech_confidence": 0.07843017578125,
             "text": " Physics works and I am still alive.",
             "time_interval": {
-                "start": 199.0,
-                "end": 205.0
+                "end": 205.0,
+                "start": 199.0
             },
-            "confidence": 0.8780664047938203,
-            "no_speech_confidence": 0.07843017578125,
             "words": []
         },
         {
+            "confidence": 0.8780664047938203,
+            "no_speech_confidence": 0.07843017578125,
             "text": " Physics works and I am still alive.",
             "time_interval": {
-                "start": 205.0,
-                "end": 211.0
+                "end": 211.0,
+                "start": 205.0
             },
-            "confidence": 0.8780664047938203,
-            "no_speech_confidence": 0.07843017578125,
             "words": []
         },
         {
+            "confidence": 0.8780664047938203,
+            "no_speech_confidence": 0.07843017578125,
             "text": " Physics works and I am still alive.",
             "time_interval": {
-                "start": 211.0,
-                "end": 217.0
+                "end": 217.0,
+                "start": 211.0
             },
-            "confidence": 0.8780664047938203,
-            "no_speech_confidence": 0.07843017578125,
             "words": []
         },
         {
+            "confidence": 0.8780664047938203,
+            "no_speech_confidence": 0.07843017578125,
             "text": " Physics works and I am still alive.",
             "time_interval": {
-                "start": 217.0,
-                "end": 223.0
+                "end": 223.0,
+                "start": 217.0
             },
-            "confidence": 0.8780664047938203,
-            "no_speech_confidence": 0.07843017578125,
             "words": []
         },
         {
+            "confidence": 0.8780664047938203,
+            "no_speech_confidence": 0.07843017578125,
             "text": " Physics works and I am still alive.",
             "time_interval": {
-                "start": 223.0,
-                "end": 227.0
+                "end": 227.0,
+                "start": 223.0
             },
-            "confidence": 0.8780664047938203,
-            "no_speech_confidence": 0.07843017578125,
             "words": []
         }
     ],
-    "info": {
-        "language": "en",
-        "language_confidence": 0.982421875
-    },
-    "execution_time": {
-        "whisper_params": 0,
-        "video": 0,
-        "download_video": 0,
-        "whisper_medium_transcribe_video": 0,
-        "media_id": 0,
-        "load_video_transcription": 0.006411314010620117,
-        "save_video": 0,
-        "delete_media": 0,
-        "save_video_transcription": 0
+    "transcription": {
+        "text": " Now I want to return to the conservation of mechanical energy.\n I have here a pendulum.\n I have an object that weighs 15 kilograms\n and I can lift it up one meter, which I have done now.\n If I let it fall, then that will be converted to kinetic energy.\n If I would let it swing from one meter height\n and you would be there and it would hit you, you'd be dead.\n 150 joules is enough to kill you.\n They use them to demolish buildings.\n You lift up a very heavy object, even heavier than this,\n and then you let it go, you swing it,\n thereby converting gravitational potential energy into kinetic energy\n which is the whole idea of wrecking.\n So you are using then the conversion of gravitational potential energy to kinetic energy.\n Now, I am such a strong believer of the conservation of mechanical energy\n that I am willing to put my life on the line.\n If I release that bob from a certain height,\n then that bob can never come back to a point where the height is any larger.\n If I release it from this height and it swings,\n then when it reaches here, it could not be higher.\n It could go from gravitational potential energy to kinetic energy\n back to gravitational potential energy and it will come to a stop here.\n And when it swings back, it should not be able to reach any higher\n provided that I do not give this object an initial speed when I stand here.\n I may not trust myself.\n I am going to release this object and I hope I will be able to do it at zero speed\n so that when it comes back it may touch my chin but it may not crush my chin.\n I want you to be extremely quiet because this is no joke.\n If I release this object at zero speed, then this will be my last lecture.\n I will close my eyes. I don't want to see this.\n So please be very quiet. I almost didn't sleep all night.\n Three, two, one, zero.\n Physics works and I am still alive.\n Physics works and I am still alive.\n Physics works and I am still alive.\n Physics works and I am still alive.\n Physics works and I am still alive."
     }
 }
\ No newline at end of file
diff --git a/aana/tests/files/expected/endpoints/whisper/video_transcribe_930699767cd541f2deb519f2f89b09d7.json b/aana/tests/files/expected/endpoints/whisper/video_transcribe_939a73622958d6746f38d629039ac1fe.json
similarity index 89%
rename from aana/tests/files/expected/endpoints/whisper/video_transcribe_930699767cd541f2deb519f2f89b09d7.json
rename to aana/tests/files/expected/endpoints/whisper/video_transcribe_939a73622958d6746f38d629039ac1fe.json
index 6eb947c9..84cb189d 100644
--- a/aana/tests/files/expected/endpoints/whisper/video_transcribe_930699767cd541f2deb519f2f89b09d7.json
+++ b/aana/tests/files/expected/endpoints/whisper/video_transcribe_939a73622958d6746f38d629039ac1fe.json
@@ -1,779 +1,779 @@
 [
     {
-        "transcription": {
-            "text": " Now I want to return to the conservation of mechanical energy."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9155454257136106,
+                "no_speech_confidence": 0.006999969482421875,
                 "text": " Now I want to return to the conservation of mechanical energy.",
                 "time_interval": {
-                    "start": 0.0,
-                    "end": 6.0
+                    "end": 6.0,
+                    "start": 0.0
                 },
-                "confidence": 0.9155454257136106,
-                "no_speech_confidence": 0.006999969482421875,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Now I want to return to the conservation of mechanical energy."
         }
     },
     {
-        "transcription": {
-            "text": " I have here a pendulum."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9155454257136106,
+                "no_speech_confidence": 0.006999969482421875,
                 "text": " I have here a pendulum.",
                 "time_interval": {
-                    "start": 6.0,
-                    "end": 12.0
+                    "end": 12.0,
+                    "start": 6.0
                 },
-                "confidence": 0.9155454257136106,
-                "no_speech_confidence": 0.006999969482421875,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " I have here a pendulum."
         }
     },
     {
-        "transcription": {
-            "text": " I have an object that weighs 15 kilograms"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9155454257136106,
+                "no_speech_confidence": 0.006999969482421875,
                 "text": " I have an object that weighs 15 kilograms",
                 "time_interval": {
-                    "start": 12.0,
-                    "end": 18.0
+                    "end": 18.0,
+                    "start": 12.0
                 },
-                "confidence": 0.9155454257136106,
-                "no_speech_confidence": 0.006999969482421875,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " I have an object that weighs 15 kilograms"
         }
     },
     {
-        "transcription": {
-            "text": " and I can lift it up one meter, which I have done now."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9155454257136106,
+                "no_speech_confidence": 0.006999969482421875,
                 "text": " and I can lift it up one meter, which I have done now.",
                 "time_interval": {
-                    "start": 18.0,
-                    "end": 24.0
+                    "end": 24.0,
+                    "start": 18.0
                 },
-                "confidence": 0.9155454257136106,
-                "no_speech_confidence": 0.006999969482421875,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " and I can lift it up one meter, which I have done now."
         }
     },
     {
-        "transcription": {
-            "text": " If I let it fall, then that will be converted to kinetic energy."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8998440065155437,
+                "no_speech_confidence": 0.423828125,
                 "text": " If I let it fall, then that will be converted to kinetic energy.",
                 "time_interval": {
-                    "start": 24.0,
-                    "end": 30.0
+                    "end": 30.0,
+                    "start": 24.0
                 },
-                "confidence": 0.8998440065155437,
-                "no_speech_confidence": 0.423828125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " If I let it fall, then that will be converted to kinetic energy."
         }
     },
     {
-        "transcription": {
-            "text": " If I would let it swing from one meter height"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8998440065155437,
+                "no_speech_confidence": 0.423828125,
                 "text": " If I would let it swing from one meter height",
                 "time_interval": {
-                    "start": 30.0,
-                    "end": 36.0
+                    "end": 36.0,
+                    "start": 30.0
                 },
-                "confidence": 0.8998440065155437,
-                "no_speech_confidence": 0.423828125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " If I would let it swing from one meter height"
         }
     },
     {
-        "transcription": {
-            "text": " and you would be there and it would hit you, you'd be dead."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8998440065155437,
+                "no_speech_confidence": 0.423828125,
                 "text": " and you would be there and it would hit you, you'd be dead.",
                 "time_interval": {
-                    "start": 36.0,
-                    "end": 42.0
+                    "end": 42.0,
+                    "start": 36.0
                 },
-                "confidence": 0.8998440065155437,
-                "no_speech_confidence": 0.423828125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " and you would be there and it would hit you, you'd be dead."
         }
     },
     {
-        "transcription": {
-            "text": " 150 joules is enough to kill you."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8998440065155437,
+                "no_speech_confidence": 0.423828125,
                 "text": " 150 joules is enough to kill you.",
                 "time_interval": {
-                    "start": 42.0,
-                    "end": 48.0
+                    "end": 48.0,
+                    "start": 42.0
                 },
-                "confidence": 0.8998440065155437,
-                "no_speech_confidence": 0.423828125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " 150 joules is enough to kill you."
         }
     },
     {
-        "transcription": {
-            "text": " They use them to demolish buildings."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8811879148457943,
+                "no_speech_confidence": 0.59521484375,
                 "text": " They use them to demolish buildings.",
                 "time_interval": {
-                    "start": 48.0,
-                    "end": 54.0
+                    "end": 54.0,
+                    "start": 48.0
                 },
-                "confidence": 0.8811879148457943,
-                "no_speech_confidence": 0.59521484375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " They use them to demolish buildings."
         }
     },
     {
-        "transcription": {
-            "text": " You lift up a very heavy object, even heavier than this,"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8811879148457943,
+                "no_speech_confidence": 0.59521484375,
                 "text": " You lift up a very heavy object, even heavier than this,",
                 "time_interval": {
-                    "start": 54.0,
-                    "end": 60.0
+                    "end": 60.0,
+                    "start": 54.0
                 },
-                "confidence": 0.8811879148457943,
-                "no_speech_confidence": 0.59521484375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " You lift up a very heavy object, even heavier than this,"
         }
     },
     {
-        "transcription": {
-            "text": " and then you let it go, you swing it,"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8811879148457943,
+                "no_speech_confidence": 0.59521484375,
                 "text": " and then you let it go, you swing it,",
                 "time_interval": {
-                    "start": 60.0,
-                    "end": 66.0
+                    "end": 66.0,
+                    "start": 60.0
                 },
-                "confidence": 0.8811879148457943,
-                "no_speech_confidence": 0.59521484375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " and then you let it go, you swing it,"
         }
     },
     {
-        "transcription": {
-            "text": " thereby converting gravitational potential energy into kinetic energy"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8811879148457943,
+                "no_speech_confidence": 0.59521484375,
                 "text": " thereby converting gravitational potential energy into kinetic energy",
                 "time_interval": {
-                    "start": 66.0,
-                    "end": 72.0
+                    "end": 72.0,
+                    "start": 66.0
                 },
-                "confidence": 0.8811879148457943,
-                "no_speech_confidence": 0.59521484375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " thereby converting gravitational potential energy into kinetic energy"
         }
     },
     {
-        "transcription": {
-            "text": " which is the whole idea of wrecking."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8715343445859605,
+                "no_speech_confidence": 0.40087890625,
                 "text": " which is the whole idea of wrecking.",
                 "time_interval": {
-                    "start": 72.0,
-                    "end": 78.0
+                    "end": 78.0,
+                    "start": 72.0
                 },
-                "confidence": 0.8715343445859605,
-                "no_speech_confidence": 0.40087890625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " which is the whole idea of wrecking."
         }
     },
     {
-        "transcription": {
-            "text": " So you are using then the conversion of gravitational potential energy to kinetic energy."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8715343445859605,
+                "no_speech_confidence": 0.40087890625,
                 "text": " So you are using then the conversion of gravitational potential energy to kinetic energy.",
                 "time_interval": {
-                    "start": 78.0,
-                    "end": 84.0
+                    "end": 84.0,
+                    "start": 78.0
                 },
-                "confidence": 0.8715343445859605,
-                "no_speech_confidence": 0.40087890625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " So you are using then the conversion of gravitational potential energy to kinetic energy."
         }
     },
     {
-        "transcription": {
-            "text": " Now, I am such a strong believer of the conservation of mechanical energy"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8715343445859605,
+                "no_speech_confidence": 0.40087890625,
                 "text": " Now, I am such a strong believer of the conservation of mechanical energy",
                 "time_interval": {
-                    "start": 84.0,
-                    "end": 90.0
+                    "end": 90.0,
+                    "start": 84.0
                 },
-                "confidence": 0.8715343445859605,
-                "no_speech_confidence": 0.40087890625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Now, I am such a strong believer of the conservation of mechanical energy"
         }
     },
     {
-        "transcription": {
-            "text": " that I am willing to put my life on the line."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8715343445859605,
+                "no_speech_confidence": 0.40087890625,
                 "text": " that I am willing to put my life on the line.",
                 "time_interval": {
-                    "start": 90.0,
-                    "end": 96.0
+                    "end": 96.0,
+                    "start": 90.0
                 },
-                "confidence": 0.8715343445859605,
-                "no_speech_confidence": 0.40087890625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " that I am willing to put my life on the line."
         }
     },
     {
-        "transcription": {
-            "text": " If I release that bob from a certain height,"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9383433771074657,
+                "no_speech_confidence": 0.01447296142578125,
                 "text": " If I release that bob from a certain height,",
                 "time_interval": {
-                    "start": 97.0,
-                    "end": 103.0
+                    "end": 103.0,
+                    "start": 97.0
                 },
-                "confidence": 0.9383433771074657,
-                "no_speech_confidence": 0.01447296142578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " If I release that bob from a certain height,"
         }
     },
     {
-        "transcription": {
-            "text": " then that bob can never come back to a point where the height is any larger."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9383433771074657,
+                "no_speech_confidence": 0.01447296142578125,
                 "text": " then that bob can never come back to a point where the height is any larger.",
                 "time_interval": {
-                    "start": 103.0,
-                    "end": 109.0
+                    "end": 109.0,
+                    "start": 103.0
                 },
-                "confidence": 0.9383433771074657,
-                "no_speech_confidence": 0.01447296142578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " then that bob can never come back to a point where the height is any larger."
         }
     },
     {
-        "transcription": {
-            "text": " If I release it from this height and it swings,"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9383433771074657,
+                "no_speech_confidence": 0.01447296142578125,
                 "text": " If I release it from this height and it swings,",
                 "time_interval": {
-                    "start": 111.0,
-                    "end": 117.0
+                    "end": 117.0,
+                    "start": 111.0
                 },
-                "confidence": 0.9383433771074657,
-                "no_speech_confidence": 0.01447296142578125,
                 "words": []
-            }
-        ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+            }
+        ],
+        "transcription": {
+            "text": " If I release it from this height and it swings,"
         }
     },
     {
-        "transcription": {
-            "text": " then when it reaches here, it could not be higher."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9383433771074657,
+                "no_speech_confidence": 0.01447296142578125,
                 "text": " then when it reaches here, it could not be higher.",
                 "time_interval": {
-                    "start": 117.0,
-                    "end": 121.0
+                    "end": 121.0,
+                    "start": 117.0
                 },
-                "confidence": 0.9383433771074657,
-                "no_speech_confidence": 0.01447296142578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " then when it reaches here, it could not be higher."
         }
     },
     {
-        "transcription": {
-            "text": " It could go from gravitational potential energy to kinetic energy"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8513452785243097,
+                "no_speech_confidence": 0.2396240234375,
                 "text": " It could go from gravitational potential energy to kinetic energy",
                 "time_interval": {
-                    "start": 121.0,
-                    "end": 127.0
+                    "end": 127.0,
+                    "start": 121.0
                 },
-                "confidence": 0.8513452785243097,
-                "no_speech_confidence": 0.2396240234375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " It could go from gravitational potential energy to kinetic energy"
         }
     },
     {
-        "transcription": {
-            "text": " back to gravitational potential energy and it will come to a stop here."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8513452785243097,
+                "no_speech_confidence": 0.2396240234375,
                 "text": " back to gravitational potential energy and it will come to a stop here.",
                 "time_interval": {
-                    "start": 127.0,
-                    "end": 133.0
+                    "end": 133.0,
+                    "start": 127.0
                 },
-                "confidence": 0.8513452785243097,
-                "no_speech_confidence": 0.2396240234375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " back to gravitational potential energy and it will come to a stop here."
         }
     },
     {
-        "transcription": {
-            "text": " And when it swings back, it should not be able to reach any higher"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8513452785243097,
+                "no_speech_confidence": 0.2396240234375,
                 "text": " And when it swings back, it should not be able to reach any higher",
                 "time_interval": {
-                    "start": 133.0,
-                    "end": 139.0
+                    "end": 139.0,
+                    "start": 133.0
                 },
-                "confidence": 0.8513452785243097,
-                "no_speech_confidence": 0.2396240234375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " And when it swings back, it should not be able to reach any higher"
         }
     },
     {
-        "transcription": {
-            "text": " provided that I do not give this object an initial speed when I stand here."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8513452785243097,
+                "no_speech_confidence": 0.2396240234375,
                 "text": " provided that I do not give this object an initial speed when I stand here.",
                 "time_interval": {
-                    "start": 139.0,
-                    "end": 145.0
+                    "end": 145.0,
+                    "start": 139.0
                 },
-                "confidence": 0.8513452785243097,
-                "no_speech_confidence": 0.2396240234375,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " provided that I do not give this object an initial speed when I stand here."
         }
     },
     {
-        "transcription": {
-            "text": " I may not trust myself."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9217725291204704,
+                "no_speech_confidence": 0.0235748291015625,
                 "text": " I may not trust myself.",
                 "time_interval": {
-                    "start": 145.0,
-                    "end": 151.0
+                    "end": 151.0,
+                    "start": 145.0
                 },
-                "confidence": 0.9217725291204704,
-                "no_speech_confidence": 0.0235748291015625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " I may not trust myself."
         }
     },
     {
-        "transcription": {
-            "text": " I am going to release this object and I hope I will be able to do it at zero speed"
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9217725291204704,
+                "no_speech_confidence": 0.0235748291015625,
                 "text": " I am going to release this object and I hope I will be able to do it at zero speed",
                 "time_interval": {
-                    "start": 151.0,
-                    "end": 157.0
+                    "end": 157.0,
+                    "start": 151.0
                 },
-                "confidence": 0.9217725291204704,
-                "no_speech_confidence": 0.0235748291015625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " I am going to release this object and I hope I will be able to do it at zero speed"
         }
     },
     {
-        "transcription": {
-            "text": " so that when it comes back it may touch my chin but it may not crush my chin."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9217725291204704,
+                "no_speech_confidence": 0.0235748291015625,
                 "text": " so that when it comes back it may touch my chin but it may not crush my chin.",
                 "time_interval": {
-                    "start": 157.0,
-                    "end": 163.0
+                    "end": 163.0,
+                    "start": 157.0
                 },
-                "confidence": 0.9217725291204704,
-                "no_speech_confidence": 0.0235748291015625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " so that when it comes back it may touch my chin but it may not crush my chin."
         }
     },
     {
-        "transcription": {
-            "text": " I want you to be extremely quiet because this is no joke."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.9217725291204704,
+                "no_speech_confidence": 0.0235748291015625,
                 "text": " I want you to be extremely quiet because this is no joke.",
                 "time_interval": {
-                    "start": 163.0,
-                    "end": 169.0
+                    "end": 169.0,
+                    "start": 163.0
                 },
-                "confidence": 0.9217725291204704,
-                "no_speech_confidence": 0.0235748291015625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " I want you to be extremely quiet because this is no joke."
         }
     },
     {
-        "transcription": {
-            "text": " If I release this object at zero speed, then this will be my last lecture."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8646648422853658,
+                "no_speech_confidence": 0.429931640625,
                 "text": " If I release this object at zero speed, then this will be my last lecture.",
                 "time_interval": {
-                    "start": 169.0,
-                    "end": 175.0
+                    "end": 175.0,
+                    "start": 169.0
                 },
-                "confidence": 0.8646648422853658,
-                "no_speech_confidence": 0.429931640625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " If I release this object at zero speed, then this will be my last lecture."
         }
     },
     {
-        "transcription": {
-            "text": " I will close my eyes. I don't want to see this."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8646648422853658,
+                "no_speech_confidence": 0.429931640625,
                 "text": " I will close my eyes. I don't want to see this.",
                 "time_interval": {
-                    "start": 175.0,
-                    "end": 181.0
+                    "end": 181.0,
+                    "start": 175.0
                 },
-                "confidence": 0.8646648422853658,
-                "no_speech_confidence": 0.429931640625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " I will close my eyes. I don't want to see this."
         }
     },
     {
-        "transcription": {
-            "text": " So please be very quiet. I almost didn't sleep all night."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8646648422853658,
+                "no_speech_confidence": 0.429931640625,
                 "text": " So please be very quiet. I almost didn't sleep all night.",
                 "time_interval": {
-                    "start": 181.0,
-                    "end": 187.0
+                    "end": 187.0,
+                    "start": 181.0
                 },
-                "confidence": 0.8646648422853658,
-                "no_speech_confidence": 0.429931640625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " So please be very quiet. I almost didn't sleep all night."
         }
     },
     {
-        "transcription": {
-            "text": " Three, two, one, zero."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8646648422853658,
+                "no_speech_confidence": 0.429931640625,
                 "text": " Three, two, one, zero.",
                 "time_interval": {
-                    "start": 187.0,
-                    "end": 193.0
+                    "end": 193.0,
+                    "start": 187.0
                 },
-                "confidence": 0.8646648422853658,
-                "no_speech_confidence": 0.429931640625,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Three, two, one, zero."
         }
     },
     {
-        "transcription": {
-            "text": " Physics works and I am still alive."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8780664047938203,
+                "no_speech_confidence": 0.07843017578125,
                 "text": " Physics works and I am still alive.",
                 "time_interval": {
-                    "start": 199.0,
-                    "end": 205.0
+                    "end": 205.0,
+                    "start": 199.0
                 },
-                "confidence": 0.8780664047938203,
-                "no_speech_confidence": 0.07843017578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Physics works and I am still alive."
         }
     },
     {
-        "transcription": {
-            "text": " Physics works and I am still alive."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8780664047938203,
+                "no_speech_confidence": 0.07843017578125,
                 "text": " Physics works and I am still alive.",
                 "time_interval": {
-                    "start": 205.0,
-                    "end": 211.0
+                    "end": 211.0,
+                    "start": 205.0
                 },
-                "confidence": 0.8780664047938203,
-                "no_speech_confidence": 0.07843017578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Physics works and I am still alive."
         }
     },
     {
-        "transcription": {
-            "text": " Physics works and I am still alive."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8780664047938203,
+                "no_speech_confidence": 0.07843017578125,
                 "text": " Physics works and I am still alive.",
                 "time_interval": {
-                    "start": 211.0,
-                    "end": 217.0
+                    "end": 217.0,
+                    "start": 211.0
                 },
-                "confidence": 0.8780664047938203,
-                "no_speech_confidence": 0.07843017578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Physics works and I am still alive."
         }
     },
     {
-        "transcription": {
-            "text": " Physics works and I am still alive."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8780664047938203,
+                "no_speech_confidence": 0.07843017578125,
                 "text": " Physics works and I am still alive.",
                 "time_interval": {
-                    "start": 217.0,
-                    "end": 223.0
+                    "end": 223.0,
+                    "start": 217.0
                 },
-                "confidence": 0.8780664047938203,
-                "no_speech_confidence": 0.07843017578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Physics works and I am still alive."
         }
     },
     {
-        "transcription": {
-            "text": " Physics works and I am still alive."
+        "info": {
+            "language": "en",
+            "language_confidence": 0.982421875
         },
         "segments": [
             {
+                "confidence": 0.8780664047938203,
+                "no_speech_confidence": 0.07843017578125,
                 "text": " Physics works and I am still alive.",
                 "time_interval": {
-                    "start": 223.0,
-                    "end": 227.0
+                    "end": 227.0,
+                    "start": 223.0
                 },
-                "confidence": 0.8780664047938203,
-                "no_speech_confidence": 0.07843017578125,
                 "words": []
             }
         ],
-        "info": {
-            "language": "en",
-            "language_confidence": 0.982421875
+        "transcription": {
+            "text": " Physics works and I am still alive."
         }
     },
     {
diff --git a/aana/tests/integration/test_chat_with_video.py b/aana/tests/integration/test_chat_with_video.py
index b786b8ae..649f457b 100644
--- a/aana/tests/integration/test_chat_with_video.py
+++ b/aana/tests/integration/test_chat_with_video.py
@@ -21,35 +21,48 @@
 )
 @pytest.mark.parametrize("call_endpoint", [TARGET], indirect=True)
 @pytest.mark.parametrize(
-    "video",
+    "video, whisper_params",
     [
-        {
-            "url": "https://mobius-public.s3.eu-west-1.amazonaws.com/squirrel.mp4",
-            "media_id": "squirrel.mp4",
-        },
-        {
-            "path": str(resources.path("aana.tests.files.videos", "physicsworks.webm")),
-            "media_id": "physicsworks.webm",
-        },
-        {
+        (
+            
+            {
+                "url": "https://mobius-public.s3.eu-west-1.amazonaws.com/squirrel.mp4",
+                "media_id": "squirrel.mp4",
+            }, {
+                "temperature": 0.0
+            }
+        ),
+        (
+            {
+                "path": str(resources.path("aana.tests.files.videos", "physicsworks.webm")),
+                "media_id": "physicsworks.webm",
+            }, {
+                "temperature": 0.0
+            }
+        ),
+        (
+            {
             "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
             "media_id": "dQw4w9WgXcQ",
-        },
+            }, {
+                "temperature": 0.0
+            }
+        )
     ],
 )
-def test_chat_with_video(call_endpoint, video):
+def test_chat_with_video(call_endpoint, video, whisper_params):
     """Test chat with video endpoint."""
     media_id = video["media_id"]
 
     call_endpoint(
         VIDEO_INDEX_ENDPOINT,
-        {"video": video},
+        {"video": video, "whisper_params": whisper_params},
     )
 
     # if we try to index the same video again, we should get an error MediaIdAlreadyExistsException
     call_endpoint(
         VIDEO_INDEX_ENDPOINT,
-        {"video": video},
+        {"video": video, "whisper_params": whisper_params},
         expected_error="MediaIdAlreadyExistsException",
     )
 
@@ -76,7 +89,7 @@ def test_chat_with_video(call_endpoint, video):
     # after deleting the video, we should be able to index it again
     call_endpoint(
         VIDEO_INDEX_ENDPOINT,
-        {"video": video},
+        {"video": video, "whisper_params": whisper_params},
     )
 
     # load video metadata
diff --git a/aana/tests/integration/test_whisper.py b/aana/tests/integration/test_whisper.py
index 0022b310..f49293b1 100644
--- a/aana/tests/integration/test_whisper.py
+++ b/aana/tests/integration/test_whisper.py
@@ -20,22 +20,24 @@
 )
 @pytest.mark.parametrize("call_endpoint", [TARGET], indirect=True)
 @pytest.mark.parametrize(
-    "video",
+    "video, whisper_params",
     [
-        {
+        ({
             "path": str(resources.path("aana.tests.files.videos", "physicsworks.webm")),
             "media_id": "physicsworks.webm",
-        }
+        }, {
+            "temperature": 0.0
+        }),
     ],
 )
-def test_video_transcribe(call_endpoint, video):
+def test_video_transcribe(call_endpoint, video, whisper_params):
     """Test video transcribe endpoint."""
     media_id = video["media_id"]
 
     # transcribe video
     call_endpoint(
         VIDEO_TRANSCRIBE_ENDPOINT,
-        {"video": video},
+        {"video": video, "whisper_params": whisper_params},
     )
 
     # load transcription
@@ -47,7 +49,7 @@ def test_video_transcribe(call_endpoint, video):
     # try to transcribe video again, it should fail with MediaIdAlreadyExistsException
     call_endpoint(
         VIDEO_TRANSCRIBE_ENDPOINT,
-        {"video": video},
+        {"video": video, "whisper_params": whisper_params},
         expected_error="MediaIdAlreadyExistsException",
     )
 
@@ -75,5 +77,5 @@ def test_video_transcribe(call_endpoint, video):
     # transcribe video again after deleting it
     call_endpoint(
         VIDEO_TRANSCRIBE_ENDPOINT,
-        {"video": video},
+        {"video": video, "whisper_params": whisper_params},
     )