@squidcloud/client
    Preparing search index...

    Interface BaseOpenAiAudioTranscribeOptions

    Base options shared by all OpenAI audio transcription models.

    interface BaseOpenAiAudioTranscribeOptions {
        modelName: "whisper-1" | "gpt-4o-transcribe" | "gpt-4o-mini-transcribe";
        prompt?: string;
        temperature?: number;
    }

    Hierarchy (View Summary)

    Index

    Properties

    modelName: "whisper-1" | "gpt-4o-transcribe" | "gpt-4o-mini-transcribe"

    Specifies the model for audio transcription.

    prompt?: string

    An optional prompt to guide the transcription process.

    temperature?: number

    The temperature for sampling during transcription; defaults to model-specific value.