Livekit is a powerful, open-source WebRTC server and client SDK that enables real-time audio communication. It’s designed for applications that require robust, scalable real-time features.
To start the Livekit server, run the following command:
Copy
Ask AI
poetry run 01 --server livekit
To generate a QR code for scanning
Copy
Ask AI
poetry run 01 --server livekit --qr
To expose over the internet via ngrok
Copy
Ask AI
poetry run 01 --server livekit --expose
In order to use the mobile app over the web, use both flags
Copy
Ask AI
poetry run 01 --server livekit --qr --expose
Currently, our Livekit server only works with Deepgram and Eleven Labs. We are
working to introduce all-local functionality as soon as possible. By setting
your profile (see Configure Your Profile), you can
still change your LLM to be a local LLM, but the interpreter.tts value will
be ignored for the Livekit server.
Livekit Server: Designed for devices with higher processing power, such as phones, web browsers, and more capable hardware. It offers a full range of features and robust performance.
Light Server: We have another lightweight server called the Light server, specifically designed for ESP32 devices. It’s optimized for low-power, constrained environments.
Livekit provides SDKs for various programming languages and platforms, allowing you to easily integrate real-time communication features into your applications.