Fact · Speech recognition
OpenAI says its gpt-realtime-whisper transcription model requires turn detection to be omitted or set to null, unlike models that default to server voice activity detection.
Checked against its source on October 17, 2026
In the source's own words
“gpt-live-transcribe and gpt-realtime-whisper require turn detection to be omitted or set to null”
Voice activity detection (VAD), OpenAI Realtime API, OpenAI, OpenAI Developers, n.d., Voice activity detection overview.
Open the original- What it measures
- Transcription sessions in the Realtime API. Models that support voice activity detection default to server_vad.
- What it does not show
- The guide does not say how the model finds the end of an utterance, so the client must commit audio itself.