May 24, 2024
.@pipecat_ai talking on the phone about the most UK topic possible ... tea vs coffee
- open source framework for voice AI
- low-latency pipeline architecture for transcription -> inference -> text-to-speech
- interruption handling
- extensible — write your own services and frame processors
- WebSockets, WebRTC, telephone dial-in/dial-out
- vision and multimodal (if you're not just talking on the phone!)
Pipecat dial-in on @trydaily with interruptions. Latency isn’t optimal since I’m dialling from the UK (using Skype, no less), but gosh it’s cool!
