Releases: livekit/agents
[email protected]
Patch Changes
-
avoid returning tiny frames from TTS - #747 (@theomonnom)
-
Fixing Assistant API Vision Capabilities - #771 (@keepingitneil)
[email protected]
Patch Changes
- avoid returning tiny frames from TTS - #747 (@theomonnom)
[email protected]
Patch Changes
-
avoid returning tiny frames from TTS - #747 (@theomonnom)
-
11labs: send phoneme in one entire xml chunk - #766 (@theomonnom)
[email protected]
Patch Changes
- avoid returning tiny frames from TTS - #747 (@theomonnom)
[email protected]
Minor Changes
Patch Changes
-
improve graceful shutdown - #756 (@theomonnom)
-
avoid returning tiny frames from TTS - #747 (@theomonnom)
-
windows: default to threaded executor & fix dev mode - #755 (@theomonnom)
-
11labs: send phoneme in one entire xml chunk - #766 (@theomonnom)
-
fix: process not starting if num_idle_processes is zero - #763 (@theomonnom)
-
voiceassistant: avoid tiny frames on playout - #750 (@theomonnom)
-
voiceassistant: expose turn_completion_delay - #752 (@theomonnom)
-
limit concurrent process init to 1 - #751 (@theomonnom)
-
Add typing-extensions as a dependency - #778 (@keepingitneil)
-
Allow setting LLM temperature with VoiceAssistant - #741 (@davidzhao)
-
better dev defaults - #762 (@theomonnom)
-
voiceassistant: allow to cancel llm generation inside before_llm_cb - #753 (@theomonnom)
-
use os.exit to exit forcefully - #770 (@theomonnom)
[email protected]
Patch Changes
-
Introduce function calling to OpenAI Assistants - #710 (@keepingitneil)
[email protected]
Patch Changes
-
Only send actual audio to Deepgram using a basic audio RMS filter - #738 (@keepingitneil)
-
defaults to nova-2-general model - #726 (@davidzhao)
[email protected]
[email protected]
Patch Changes
- Fixes to Anthropic Function Calling - #708 (@keepingitneil)
[email protected]
Patch Changes
- tts_forwarder: don't raise inside mark_{audio,text}_segment_end when nothing was pushed - #730 (@theomonnom)