Merge pull request #3930 from dakshdua/main

Add `push_empty_transcripts` param to `BaseWhisperSTTService` to push received empty transcripts downstream
This commit is contained in:
Mark Backman
2026-03-05 19:25:15 -05:00
committed by GitHub
2 changed files with 13 additions and 3 deletions

1
changelog/3930.added.md Normal file
View File

@@ -0,0 +1 @@
- Added `push_empty_transcripts` parameter to `BaseWhisperSTTService` and `OpenAISTTService` to allow empty transcripts to be pushed downstream as `TranscriptionFrame` instead of discarding them (the default behavior). This is intended for situations where VAD fires even though the user did not speak. In these cases, it is useful to know that nothing was transcribed so that the agent can resume speaking, instead of waiting longer for a transcription.