Interface TranscriptionSession

A new Realtime transcription session configuration.

When a session is created on the server via REST API, the session object also contains an ephemeral key. Default TTL for keys is 10 minutes. This property is not present when a session is updated via the WebSocket API.

interface TranscriptionSession {
    client_secret: OpenAIClient.Beta.Realtime.TranscriptionSessions.TranscriptionSession.ClientSecret;
    input_audio_format?: string;
    input_audio_transcription?: OpenAIClient.Beta.Realtime.TranscriptionSessions.TranscriptionSession.InputAudioTranscription;
    modalities?: ("text" | "audio")[];
    turn_detection?: OpenAIClient.Beta.Realtime.TranscriptionSessions.TranscriptionSession.TurnDetection;
}

Properties

client_secret input_audio_format? input_audio_transcription? modalities? turn_detection?

Properties

client_secret

client_secret: OpenAIClient.Beta.Realtime.TranscriptionSessions.TranscriptionSession.ClientSecret

Ephemeral key returned by the API. Only present when the session is created on the server via REST API.

Optionalinput_audio_format

input_audio_format?: string

The format of input audio. Options are pcm16, g711_ulaw, or g711_alaw.

Optionalinput_audio_transcription

input_audio_transcription?: OpenAIClient.Beta.Realtime.TranscriptionSessions.TranscriptionSession.InputAudioTranscription

Configuration of the transcription model.

Optionalmodalities

modalities?: ("text" | "audio")[]

The set of modalities the model can respond with. To disable audio, set this to ["text"].

Optionalturn_detection

turn_detection?: OpenAIClient.Beta.Realtime.TranscriptionSessions.TranscriptionSession.TurnDetection

Configuration for turn detection. Can be set to null to turn off. Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech.

Settings

Member Visibility

On This Page

Properties