Interface SpeechCreateParams

interface SpeechCreateParams {
    input: string;
    instructions?: string;
    model: string & {} | OpenAIClient.Audio.Speech.SpeechModel;
    response_format?:
        | "wav"
        | "aac"
        | "mp3"
        | "flac"
        | "opus"
        | "pcm";
    speed?: number;
    stream_format?: "audio" | "sse";
    voice:
        | string & {}
        | "alloy"
        | "ash"
        | "ballad"
        | "coral"
        | "echo"
        | "sage"
        | "shimmer"
        | "verse";
}

Properties

input instructions? model response_format? speed? stream_format? voice

Properties

input

input: string

The text to generate audio for. The maximum length is 4096 characters.

Optionalinstructions

instructions?: string

Control the voice of your generated audio with additional instructions. Does not work with tts-1 or tts-1-hd.

model

model: string & {} | OpenAIClient.Audio.Speech.SpeechModel

One of the available TTS models: tts-1, tts-1-hd or gpt-4o-mini-tts.

Optionalresponse_format

response_format?:
    | "wav"
    | "aac"
    | "mp3"
    | "flac"
    | "opus"
    | "pcm"

The format to audio in. Supported formats are mp3, opus, aac, flac, wav, and pcm.

Optionalspeed

speed?: number

The speed of the generated audio. Select a value from 0.25 to 4.0. 1.0 is the default.

Optionalstream_format

stream_format?: "audio" | "sse"

The format to stream the audio in. Supported formats are sse and audio. sse is not supported for tts-1 or tts-1-hd.

voice

voice:
    | string & {}
    | "alloy"
    | "ash"
    | "ballad"
    | "coral"
    | "echo"
    | "sage"
    | "shimmer"
    | "verse"

The voice to use when generating the audio. Supported voices are alloy, ash, ballad, coral, echo, fable, onyx, nova, sage, shimmer, and verse. Previews of the voices are available in the Text to speech guide.

Settings

Member Visibility

On This Page

Properties