Hacker News new | ask | show | jobs
by davidz 618 days ago
Currently it does: all audio is sent to the model.

However, we are working on turn detection within the framework, so you won't have to send silence to the model when the user isn't talking. It's a fairly straight forward path to cutting down the cost by ~50%.
2 comments
rukuu001 617 days ago
Working on this for an internal tool - detecting no speech has been a PITA so far. Interested to see how you go with this.
link
balloob 617 days ago
Use the voice activity detector we wrote for Home Assistant. It works very well: https://github.com/rhasspy/pymicro-vad
link
ValentinA23 617 days ago
What if I'm watching TV and use the AI to control it ? It should only react to my voice (a problem I had that forced me to use a wake word).
link
davidz 617 days ago
currently we are using silero VAD to detect speech: https://github.com/livekit/agents/blob/main/livekit-plugins/...

it works well for voice activity; though it doesn't always detect end-of-turn correctly (humans often pause mid-sentence to think). we are working on improving this behavior.

link
pj_mukh 617 days ago
Can I currently put a VAD module in the pipeline and only send audio when there is an active conversation? Feel like just that would solve the problem?
link