@squidcloud/client
    Preparing search index...

    Interface OpenAiCreateSpeechOptions

    Options for creating speech using OpenAI's text-to-speech models.

    interface OpenAiCreateSpeechOptions {
        instructions?: string;
        modelName: "tts-1" | "tts-1-hd" | "gpt-4o-mini-tts";
        responseFormat?: "mp3" | "opus" | "aac" | "flac" | "wav" | "pcm";
        speed?: number;
        voice?:
            | "alloy"
            | "ash"
            | "ballad"
            | "coral"
            | "echo"
            | "fable"
            | "onyx"
            | "nova"
            | "sage"
            | "shimmer"
            | "verse";
    }

    Hierarchy (View Summary)

    Index

    Properties

    instructions? modelName responseFormat? speed? voice?

    Properties

    instructions?: string

    An optional prompt to guide the speech synthesis process.

    modelName: "tts-1" | "tts-1-hd" | "gpt-4o-mini-tts"

    The OpenAI model to use for speech creation (e.g., 'tts-1' or 'tts-1-hd').

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

    The format of the audio output; defaults to 'mp3'.

    speed?: number

    The speed of the speech; defaults to 1.0.

    voice?:
        | "alloy"
        | "ash"
        | "ballad"
        | "coral"
        | "echo"
        | "fable"
        | "onyx"
        | "nova"
        | "sage"
        | "shimmer"
        | "verse"

    The voice to use for speech synthesis; defaults to model-specific value.

    Settings

    Member Visibility

    On This Page

    Properties