Source: OpenAI Realtime Voice Activity Detection Guide
OpenAI's guide to turn detection in Realtime sessions: server_vad parameters, semantic_vad with eagerness, events and trade-offs.
Contents
- What: official API documentation (Voice activity detection)
- Author/publisher: OpenAI
- Date: living document; read 2026-11-14
- Original: Voice activity detection
Summary
Explains the two automatic turn-detection modes of the Realtime API and how to tune them.
Key claims
- VAD is on by default in speech-to-speech sessions; configured at
session.audio.input.turn_detection; default modeserver_vad. server_vadis silence-based:threshold(0-1, higher for noisy rooms),prefix_padding_ms,silence_duration_ms(shorter = faster turns, more cut-offs), pluscreate_responseandinterrupt_response.semantic_vaduses a classifier on the user’s words to score whether they have finished; low probability waits for a timeout.eagerness=low/medium(auto, the default) /hightunes how long it waits (the guide gives no numeric wait times).- Semantic VAD makes premature interruptions and split transcripts less likely.
- Events:
input_audio_buffer.speech_startedandinput_audio_buffer.speech_stopped. - Some transcription models require turn detection off (
null), with the client sendinginput_audio_buffer.commitmanually.