Pinned
Thank you to our community, and all the Pipecat developers out there. You guys are amazing 🫡
Pipecat AI
233 posts
Pipecat AI
@pipecat_ai
100% open source framework for realtime voice and multimodal AI. Maintained by @trydaily engineering team with support from the Pipecat developer community.
Joined May 2024
- The new sonic-2 voice models from @cartesia are available in Pipecat. Latency is 40ms for the `sonic-turbo` version of the model and 90ms for the larger `sonic-2` model. - Cartesia developer docs: docs.cartesia.ai/build-with-car… - A complete voice agent example project:
- link in bio
- Today, 2:40 🙌 Open source + voice agents at the @aiDotEngineer Summit in New York. Nik from Superdial talks automating millions of healthcare calls
- Lots of new things in 0.40. ✨ Function calling and prompt caching for @AnthropicAI Claude 3.5 Sonnet ✨ Llama 3.1 function calling support in the @togethercompute service ✨ A complete implementation of the RTVI standard ✨ Studypal, a new application example from the team at
- This Thursday, Sep 4th - Voice AI Meetup in London! We love talking with you all at these meetups, and are excited to be back in the UK. Register your spot, in thread. 🍻 Networking, food, drinks with fellow voice AI engineers and teams 🫡 Live demos, panel, and chats with
- 🚀 Today we’re launching Pipecat TV! A video podcast about Pipecat: new features, how-tos, advanced tricks, community interviews & more. 🎙️ Fun + useful for all voice AI builders. Watch the pilot episode now! 🐱📺
- Pipecat 0.0.62 released today. Highlights include: ➡️ Support for @gladia_io's Solaris speech-to-text model released today. ➡️ A new memory layer service courtesy of @mem0ai. ➡️ WhisperSTTServiceMLX for Whisper transcription on Apple Silicon ➡️ A new peer-to-peer WebRTC.@gladia_io announced their new Solaria speech-to-text model today. I hear so, so many rave reviews about Gladia from people building French-language voice AI agents. Gladia's new model supports more than 100 languages. The language auto-detection is the best I've seen from any
00:00 - Here's an example of parallel pipelines and complex function calling using a speech-to-speech API.Can you beat my 1-929-LLM-GAME high score? We've been exploring what you can do with speech-to-speech models. Here's a word guessing game, built with the Gemini Multimodal Live API, Vercel, and Twilio, that has a bunch of interesting features ... 🧵
00:00 - Pipecat 0.0.37 is now available with the first RTVI-AI backend implementation! Meow!Today we’re announcing an open standard for Real-time Voice and Video Inference: RTVI-AI. The RTVI abstractions and data structures define how client applications communicate with inference services. These are the “real-time APIs” for use cases like: - Voice chat with LLMs
