asr
Real-time speech-to-text transcription channel.
Real-time speech-to-text transcription channel.
HTTP Bearer authentication. Pass the Kotoba API key as a Bearer token via the Authorization header. Server-side use only.
Must be sent exactly once after receiving transcription_session.created
and before sending audio. Sets the input audio format, sampling rate,
and transcription language.
Sends a Base64-encoded audio chunk as a JSON frame.
Sent when ending audio transmission. The server processes remaining
audio and emits a final
conversation.item.input_audio_transcription.completed.