AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

Adjustable VAD threshold for Speech to Text

xAI Grok Release Notes · article · Jul 23, 2026 · UTC

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.

Read original source ↗ Open in workspace

recordType
page-entry
evidenceStatus
publisher-reported
region
Global

Evidence & attribution

First collected: 2026-09-23T00:41:11.323Z. This is not the publication date.