wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add TTFB metrics for STT services (#3495)

Browse Source
This commit is contained in:
Mark Backman
2026-01-23 18:47:34 -05:00
committed by GitHub
parent 4ea546785f
commit bcb019e8ab
22 changed files with 309 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
changelog/3495.changed.2.md Normal file
View File

@@ -0,0 +1 @@
- `SarvamSTTService` now defaults `vad_signals` and `high_vad_sensitivity` to `None` (omitted from connection parameters), improving latency by ~300ms compared to the previous defaults.

1
changelog/3495.changed.md Normal file
View File

@@ -0,0 +1 @@
- Improved the STT TTFB (Time To First Byte) measurement, reporting the delay between when the user stops speaking and when the final transcription is received. Note: Unlike traditional TTFB which measures from a discrete request, STT services receive continuous audio input—so we measure from speech end to final transcript, which captures the latency that matters for voice AI applications. In support of this change, added `finalized` field to `TranscriptionFrame` to indicate when a transcript is the final result for an utterance.