Back
AI summary
Written by AI from the official notes. Check them for exact details.Speech to Text now allows adjustment of the voice-activity detection threshold.
- Introduced
vad_thresholdparameter for Speech to Text. - Lower values capture quieter or noisier speech.
- Setting
0disables the voice-activity gate.
Why it matters: Users needing precise control over audio transcription should consider this update for improved accuracy.
Full release notes
Speech to Text now accepts a vad_threshold parameter (streaming query param and batch multipart field) to tune the voice-activity gate that skips non-speech audio. Lower values transcribe quieter or noisier speech — useful for narrowband telephony — and 0 disables the gate. See the Speech to Text docs.