Open-Source Real-Time Voice Agent Frameworks

Frameworks like Pipecat and LiveKit Agents for building voice agents that hold a spoken conversation in real time.

13 tools
Favicon of Pipecat

Pipecat

3 videos
Open-source Python framework for voice AI agents. Run it locally or on your servers, with WebRTC and telephony support under the BSD 2-Clause license.

16KUpdated 21 hours agoBSD-2-Clause

#LLM tracing#Multi-agent workflows#Multimodal input

Favicon of Pydantic AI

Pydantic AI

4 videos
Open source Python AI agent SDK with typed outputs, Ollama support, and an optional self-hosted model gateway. Licensed MIT.

20.3KUpdated 1 hour agoMIT

#Human approval#LLM tracing#MCP

A Python voice AI agent library under the MIT license, with self-hosted telephony, OpenAI and Anthropic integrations, and local speech options.

3.8KUpdated 2 years agoMIT

Docker#Streaming inference#Tool calling

Rhasspy 3 is an early developer-preview voice assistant toolkit with Home Assistant integration and an MIT license. Archived and unmaintained.

382Updated 3 years agoMIT

#Home Assistant integration#Multilingual#Voice activity detection

A voice AI agent platform with an MIT-licensed, self-hosted Python core, Docker support, and hosted APIs for multilingual phone calls.

778Updated 2 days agoMIT

Docker#Human approval#Multilingual#Tool calling

Favicon of Moonshine

Moonshine

3 videos
An on-device AI voice toolkit for speech recognition, intent recognition and text to speech, with support for desktop, mobile, browsers and Raspberry Pi.

11.2KUpdated 1 month ago

macOS · Windows · Linux · iOS · Android · Web#Multilingual#Streaming inference

An open-source voice assistant platform for Linux, Raspberry Pi and Docker, with offline speech plugins and support for local OpenAI-compatible LLM servers.

295Updated 2 days agoApache-2.0

Linux · Docker#OpenAI-compatible API#Wake word detection#Works offline

An open-source voice assistant protocol that connects Home Assistant to speech and wake word services over a trusted network. Uses the MIT license.

397Updated 1 day agoMIT

#Home Assistant integration#Voice activity detection

An open-source voice AI agent framework for Python and Node.js. Run the stack on your own servers or use LiveKit Cloud. Licensed under Apache 2.0.

14.4KUpdated 19 hours agoApache-2.0

#MCP#Multi-agent workflows#Multimodal input

A self-hosted AI agent platform for text and voice, with business rules, conversation testing, and a shared visual and code workspace.

21.3KUpdated 9 months agoApache-2.0

Web#Guardrails#LLM tracing#MCP

An open-source voice AI framework that processes speech directly, with local inference on Mac and iPhone through MLX and self-hosted server backends.

11.2KUpdated 5 months agoApache-2.0

macOS · iOS · Web#Hugging Face integration#MLX#Quantization

A self-hosted voice AI framework with RTC and WebSocket support, Docker deployment, and examples that use OpenAI, Deepgram and Agora.

11.1KUpdated 18 hours ago

Docker · Web#Multimodal input#Voice activity detection

Open-source Python AI agent framework under MIT. Coordinate agents and tools, use local or hosted sandboxes, and connect to OpenAI or other model providers.

29.8KUpdated 23 hours agoMIT

macOS · Windows · Linux#Code execution#Guardrails#Human approval

More in Voice, Speech and Music