What are the best Python voice agents?

By maintained adoption — GitHub stars plus recent commit activity — Pipecat, LiveKit Agents and bailing lead the Python voice agents in this index of 16. The full ranking is below; it reflects what is genuinely used and still maintained, not what pays.

Are these Python voice agents open source and free?

Yes — every project on this page is open source and written primarily in Python. MIT is the most common licence here, on 9 of 16, across 4 licences in total. The software is free to run and self-host; you still pay for the infrastructure you run it on and any model or API usage it makes.

Why choose Python voice agents specifically?

Staying in your team's primary language — Python — makes self-hosting, extending, and debugging far easier, because you can read and modify the source directly instead of treating it as a black box. It also makes upstream activity something you can judge: 11 of these 16 shipped in the last 90 days, and reading a quiet project's source is how you tell finished from abandoned.

Open source · Python

Best Python voice agents

The 16 open-source voice agents written in Python in this index, ranked by real maintained adoption (GitHub stars and recent commit activity), never by sponsorship. Pipecat leads the set at 15,938 GitHub stars, and 11 of the 16 have shipped a commit in the last 90 days. Every project here is Python-first, self-hostable, and free to run; the trade-off is you host and maintain it yourself. Right now it's led by Pipecat (16k stars), with LiveKit Agents and bailing close behind. Rankings shift as projects gain stars and ship commits.

16 open-source records · all voice agents · more best-of lists · how we rank

PipecatFrameworkCompose voice and multimodal agents with Python processing pipelines.Open sourcePython · BSD-2-ClauseVerified · Active 16kGitHub stars LiveKit AgentsFrameworkBuild voice and multimodal agents that participate in LiveKit rooms.Open sourcePython · Apache-2.0Verified · Active 14kGitHub stars bailingAgentA GPT-4o-like voice conversation robot built from ASR+LLM+TTS, integrating strong models like DeepSeek R1 and openClaw -- a genuine personal voice assistant with latency as low as 800ms.Open sourcePython · MITVerified 1.8kGitHub stars CyberVersePlatformSelf hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.Open sourcePython · GPL-3.0Verified · Active 1.7kGitHub stars PatterSDK / libraryOpen-source voice-AI SDK. The Vapi/Retell alternative for builders who want to own the stack.Open sourcePython · MITVerified · Active 1.1kGitHub stars JARVISAgentYour own personal voice assistant: Voice to Text to LLM to Speech, displayed in a web interfaceOpen sourcePython · GPL-3.0Verified 528GitHub stars ai-avatar-systemAgentAI Avatar / digital human platform — upload a photo, clone a voice, talk to any face in real time with lip-sync video. Open-source, self-hosted. Claude · Whisper · Chatterbox · MuseTalk.Open sourcePython · MITVerified · Active 507GitHub stars Deepgram Python SDKSDK / libraryPython client library for Deepgram APIs; hosted service usage is separate.Open sourcePython · MITVerified · Active 468GitHub stars bolnaAgentEnd-to-end platform for building voice first multimodal agentsOpen sourcePython · MITVerified 433GitHub stars sutandoAgentMy AI Stand. Realtime by day, rewriting itself by night. Summon my AI superpower.Open sourcePython · MITVerified · Active 397GitHub stars agent-second-brainAgentAn always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vault. Runs 24/7 on the Claude subscription you already have.Open sourcePython · MITVerified 388GitHub stars LLMVoXSDK / libraryLLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLMOpen sourcePythonVerified 312GitHub stars

For agent buildersMake your product part of the discovery.Explore advertising

M.I.L.E.SAgentM.I.L.E.S, a GPT-4-Turbo voice assistant, self-adapts its prompts and AI model, can play any Spotify song, adjusts system and Spotify volume, performs calculations, browses the web and internet,Open sourcePython · MITVerified 236GitHub stars axiom-voice-agentAgentRun a <400ms latency Voice Agent on just 4GB VRAM. Fully offline, no API keys required. Optimized for GTX 1650 and edge robotics with zero-copy inference. (Apache 2.0)Open sourcePython · Apache-2.0Verified 147GitHub stars BentoVoiceAgentAgentBuild Phone Calling Voice Agent fully powered by open source models.Open sourcePythonVerified 132GitHub stars AI-Voice-AgentAgentSelf-hosted AI voice agentOpen sourcePython · MITVerified · Active 41GitHub stars

Frequently asked

What are the best Python voice agents?: By maintained adoption — GitHub stars plus recent commit activity — Pipecat, LiveKit Agents and bailing lead the Python voice agents in this index of 16. The full ranking is below; it reflects what is genuinely used and still maintained, not what pays.
Are these Python voice agents open source and free?: Yes — every project on this page is open source and written primarily in Python. MIT is the most common licence here, on 9 of 16, across 4 licences in total. The software is free to run and self-host; you still pay for the infrastructure you run it on and any model or API usage it makes.
Why choose Python voice agents specifically?: Staying in your team's primary language — Python — makes self-hosting, extending, and debugging far easier, because you can read and modify the source directly instead of treating it as a black box. It also makes upstream activity something you can judge: 11 of these 16 shipped in the last 90 days, and reading a quiet project's source is how you tell finished from abandoned.