vvzvlad/gitmost
1
0
Fork 0
Code Issues 14 Pull Requests 12 Packages Projects Releases Activity

fix(dictation): cut on ~1.5s silence instead of 0.64s

Browse Source 
Streaming dictation sends one transcription request per ended speech segment.
With redemptionMs=640 the VAD cut on every ~0.64s gap, so normal halting speech
fragmented into many segments and flooded /ai-chat/transcribe — tripping the
per-user rate limit even at modest real usage.

Raise redemptionMs to 1500 so a cut only happens on a real sentence/thought
pause (~the "couple seconds" the feature was meant to use). Request count now
tracks actual pauses rather than inter-word gaps; the server throttle is left
unchanged (the earlier limit bump was treating the symptom).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
claude_code
2026-06-22 18:04:35 +03:00
parent 6a85680a7d
commit 373c56c0d3
1 changed files with 8 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
apps/client/src/features/dictation/hooks/use-streaming-dictation.ts
View File

@@ -280,9 +280,14 @@ export function useStreamingDictation(
// positive threshold, per Silero guidance). // positive threshold, per Silero guidance).
negativeSpeechThreshold: 0.35, negativeSpeechThreshold: 0.35,
// Silence to wait through before ending a segment (the "don't cut // Silence to wait through before ending a segment (the "don't cut
// immediately" delay) — ~0.6s. NOTE: vad-web 0.0.30 takes this in ms, not // immediately" delay). Each ended segment is ONE transcription request, so
// frames (one Silero frame is ~32ms at 16k). // cutting on short gaps over-fragments normal speech into a flood of tiny
redemptionMs: 640, // requests (and trips the server's per-user rate limit). Wait ~1.5s — a
// real sentence/thought boundary — so request count tracks actual pauses,
// not every inter-word gap. Higher = fewer requests but more latency
// before text appears. NOTE: vad-web 0.0.30 takes this in ms, not frames
// (one Silero frame is ~32ms at 16k).
redemptionMs: 1500,
// Audio kept before speech start (left padding so the first word isn't // Audio kept before speech start (left padding so the first word isn't
// clipped) — ~0.3s. // clipped) — ~0.3s.
preSpeechPadMs: 320, preSpeechPadMs: 320,