playground/doc/sdk discrepancy: missing 'nova' voice in completions.create audio voices options

[superap101]

Confirm this is a Node library issue and not an underlying OpenAI API issue

• This is an issue with the Node library

Describe the bug

sdv version: 4.80.1

I've been testing in the playground the completion chat audio response.
Among the available voices, there is nova.

Once I've finished setting up the parameters I liked, I've used the code button to get the code to insert in my project.

I get an error here:

const resp = await openai.chat.completions.create({
    messages: chatMessages,
    temperature,
    tools,
    model,
    modalities,
    audio: {voice:"nova", format:"wav"},//  here
})

No overload matches this call.
Overload 1 of 3, '(body: ChatCompletionCreateParamsNonStreaming, options?: RequestOptions | undefined): APIPromise', gave the following error.
Type '"nova"' is not assignable to type '"alloy" | "ash" | "ballad" | "coral" | "echo" | "sage" | "shimmer" | "verse"'.
Overload 2 of 3, '(body: ChatCompletionCreateParamsStreaming, options?: RequestOptions | undefined): APIPromise<Stream>', gave the following error.
Type '"nova"' is not assignable to type '"alloy" | "ash" | "ballad" | "coral" | "echo" | "sage" | "shimmer" | "verse"'.
Overload 3 of 3, '(body: ChatCompletionCreateParamsBase, options?: RequestOptions | undefined): APIPromise<ChatCompletion | Stream<...>>', gave the following error.
Type '"nova"' is not assignable to type '"alloy" | "ash" | "ballad" | "coral" | "echo" | "sage" | "shimmer" | "verse"'.ts(2769)

In the sdk:

/**
 * Parameters for audio output. Required when audio output is requested with
 * `modalities: ["audio"]`.
 * [Learn more](https://platform.openai.com/docs/guides/audio).
 */
export interface ChatCompletionAudioParam {
  /**
   * Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`, `opus`,
   * or `pcm16`.
   */
  format: 'wav' | 'mp3' | 'flac' | 'opus' | 'pcm16';

  /**
   * The voice the model uses to respond. Supported voices are `ash`, `ballad`,
   * `coral`, `sage`, and `verse` (also supported but not recommended are `alloy`,
   * `echo`, and `shimmer`; these voices are less expressive).
   */
  voice: 'alloy' | 'ash' | 'ballad' | 'coral' | 'echo' | 'sage' | 'shimmer' | 'verse';
}

I'm not a dev or english native speaker, so my apologies if this report isn't clear or useful.

To Reproduce

Try this in your nodejs project:

const resp = await openai.chat.completions.create({
    messages: chatMessages,
    temperature,
    tools,
    model,
    modalities,
    audio: {voice:"nova", format:"wav"},//  here
})

Code snippets

OS

windows 10

Node version

v20.10.0

Library version

4.80.1

[kwhinnery-openai]

thanks for the report! we will get this sorted - in the meantime, the voice should still work when submitted through the SDK, it will just have a type error you will need to ignore with @ts-expect-error or similar.