agents

agents copied to clipboard

fix https://github.com/livekit/agents/issues/4048

longcw

speech_handle's _wait_for_generation hangs forever if cancelled before playout

2

if a speech handle gets cancelled before the playout has started, it's "on the queue", and authorization is cleared, but then the _wait_for_generation is never finished. I'm not sure if...

simllll

### Feature Type Would make my life easier ### Feature Description When calling `session.say` or `session.generate_reply`, if interrupted, it is hoped that the returned SpeechHandle instance can obtain the portion...

Panmax

BackgroundAudioPlayer cannot restart after being closed

1

### Bug Description Hi Team, In livekit-agents/livekit/agents/voice/background_audio.py, method `aclose` closes: ```python3 await self._audio_mixer.aclose() await self._audio_source.aclose() ``` But the `start` doesn't re-initialise them. Our current workaround is to re-create the instance,...

wdhwg001

adrian-cowham

Whatsapp calling API support

8

Could you please add support for newly introduced WhatsApp Calling API. This will be helpful to handle Whatsapp user-initiated calls by AI agents.

aiagent-dialog

Session.say audio not working since 1.3+

6

### Bug Description Since I updated to 1.3.3 from 1.2.18 I have an issue playing audios with session.say. Strange enough, it works when I run with `console` but not on...

marctorsoc

### Feature Type Would make my life easier ### Feature Description Currently Elevenlabs supports pronunciation dictionaries with most of their TTS streaming models. These provide a programmatic way of pronouncing...

arvindvs

Elevenlabs include pronunciation dictionary locators

2

arvindvs

Text input interruption prevents response generation in Gemini Live API

1

### Bug Description When using `livekit-agents[google] v1.2.18` with Gemini Live API (2.5), if a user sends text input while the model is generating a response, it successfully interrupts the model...

frankfarzan