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

Only create the EmulateUserStartedSpeakingFrame if we have received a transcription.

Browse Source
This commit is contained in:
Filipi Fuchter
2025-07-14 17:38:03 -03:00
parent 8fd5576879
commit 727af2e6fb
2 changed files with 10 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
CHANGELOG.md
View File

@@ -12,6 +12,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- For `LmntTTSService`, changed the default `model` to `blizzard`, LMNT's - For `LmntTTSService`, changed the default `model` to `blizzard`, LMNT's
recommended model. recommended model.
### Fixed
- Fixed an issue where, in some edge cases, the `EmulateUserStartedSpeakingFrame`
could be created even if we didn't have a transcription.
## [0.0.76] - 2025-07-11 ## [0.0.76] - 2025-07-11
### Added ### Added

6
src/pipecat/processors/aggregators/llm_response.py
View File

@@ -693,7 +693,11 @@ class LLMUserContextAggregator(LLMContextResponseAggregator):
# to emulate VAD (i.e. user start/stopped speaking), but we do it only # to emulate VAD (i.e. user start/stopped speaking), but we do it only
# if the bot is not speaking. If the bot is speaking and we really have # if the bot is not speaking. If the bot is speaking and we really have
# a short utterance we don't really want to interrupt the bot. # a short utterance we don't really want to interrupt the bot.
if not self._user_speaking and not self._waiting_for_aggregation: if (
not self._user_speaking
and not self._waiting_for_aggregation
and len(self._aggregation) > 0
):
if self._bot_speaking: if self._bot_speaking:
# If we reached this case and the bot is speaking, let's ignore # If we reached this case and the bot is speaking, let's ignore
# what the user said. # what the user said.