Type Alias SyncTranscriptionConfig

SyncTranscriptionConfig: {
    channels?: number;
    conversation_context?: string | string[];
    keyterms_prompt?: string[];
    language_codes?: string[];
    model?: SyncSpeechModel;
    prompt?: string;
    sample_rate?: number;
    timestamps?: boolean;
}

Options for a synchronous transcription request.

sample_rate and channels are required only for raw PCM audio — WAV carries them in its header. model is sent as the X-AAI-Model routing header and is never included in the request body.

Type declaration

  • Optionalchannels?: number

    The channel count (1 for mono, 2 for stereo). Required for raw PCM audio; ignored for WAV.

  • Optionalconversation_context?: string | string[]

    Prior turns from the same conversation, oldest first, most recent last. A single string is treated as one turn. Capped at 100 turns and 4096 characters in total — over-cap context is trimmed (oldest turns dropped first), not rejected.

  • Optionalkeyterms_prompt?: string[]

    Terms to bias the decoder towards. Whitespace is stripped and empty terms are dropped. Maximum 2048 characters in total — longer lists are rejected.

  • Optionallanguage_codes?: string[]

    ISO 639-1 codes for the language(s) of the audio — a single-element array (e.g. ["es"]) for monolingual audio, or several codes (e.g. ["en", "es"]) for multilingual audio. Ignored when prompt is set. Defaults to English.

  • Optionalmodel?: SyncSpeechModel

    The sync speech model to route to, sent as the X-AAI-Model header. Defaults to "universal-3-5-pro".

  • Optionalprompt?: string

    Custom transcription instruction. Maximum 4096 characters — longer prompts are rejected.

  • Optionalsample_rate?: number

    The source sample rate in Hz. Required for raw PCM audio; ignored for WAV.

  • Optionaltimestamps?: boolean

    Whether to compute per-word start/end timestamps. When true, words carry accurate timestamps at a small latency cost. Defaults to false: no timestamps are returned.

Settings

Member Visibility