LLMUserContextAggregator: ignore short uterrances while bot speaking

This commit is contained in:
Aleix Conchillo Flaqué
2025-04-25 11:30:00 -07:00
parent a7718926e9
commit 99a4154cbc
2 changed files with 38 additions and 11 deletions

View File

@@ -25,6 +25,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Changed
- Short utterances not detected by VAD while the bot is speaking are now
ignored. This reduces the amount of bot interruptions significantly providing
a more natural conversation experience.
- Updated `GladiaSTTService` to output a `TranslationFrame` when specifying a
`translation` and `translation_config`.