To get started pip install fastrtc

Join and Follow our org: huggingface.co/fastrtc

Check out the cookbook fastrtc.org/cookbook/ for conversational apps powered by Gemini, SambaNova, OpenAI and more!

File requests and bugs the repo: github.com/freddyaboult...

Key features:
🗣️ Automatic Voice Detection and Turn Taking
🧰 Bring any LLM, audio, or video model
💻 Automatic Gradio UI for testing
💪 Mount to any FastAPI app for production
📞 Call via Phone for Free

Check it out in action!

Read more about this in the docs!

freddyaboulton.github.io/gradio-webrt...

The magic is handled by the new `ReplyOnStopWords` stream handler. It lets you configure the stop word or phrase very easily!

The space is here: huggingface.co/spaces/fredd...

Please ⭐️ the repo: github.com/freddyaboult...

Docs: freddyaboulton.github.io/gradio-webrtc/

Repo: github.com/freddyaboult...

We want to continue focusing on chatbot/agent use cases at @gradio-hf.bsky.social . Anything we can do to make the experience better?

Thanks! Yea it's running the Moshi model (native speech-to-speech LLM) developed by kyutai. The thing I worked on was making the audio streaming low-latency and easy to implement in python

This app is written in about 100 LOC thanks to Gradio and my WebRTC extension: github.com/freddyaboult...

Check it out and give it a ⭐️ if you find it useful!

Hello! you opt-in to get credentials to access the server. It's not a dataset.