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

STTService: passthrough audio frames by default

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2025-04-24 17:13:18 -07:00
parent a753a623d4
commit 9fd76923fd
2 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
CHANGELOG.md
View File

@@ -18,6 +18,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Changed ### Changed
- STT services now passthrough audio frames by default. This allows you to add
audio recording without worrying about what's wrong in your pipeline when it
doesn't work the first time.
- Input transports now always push audio downstream unless disabled with - Input transports now always push audio downstream unless disabled with
`TransportParams.audio_in_passthrough`. After many Pipecat releases, we `TransportParams.audio_in_passthrough`. After many Pipecat releases, we
realized this is the common use case. There are use cases where the input realized this is the common use case. There are use cases where the input

2
src/pipecat/services/stt_service.py
View File

@@ -30,7 +30,7 @@ class STTService(AIService):
def __init__( def __init__(
self, self,
audio_passthrough=False, audio_passthrough=True,
# STT input sample rate # STT input sample rate
sample_rate: Optional[int] = None, sample_rate: Optional[int] = None,
**kwargs, **kwargs,