stimm-ai/stimm
The Open Source Voice Agent Platform. Orchestrate ultra-low latency AI pipelines for real-time conversations over WebRTC.
This project helps create AI voice agents that can have natural, real-time conversations, even when complex reasoning is needed in the background. It takes spoken input from a user and provides immediate, progressively refined spoken responses, making the interaction feel seamless. It's for anyone building conversational AI applications like customer support bots or virtual assistants who need their agents to sound responsive and intelligent.
Available on PyPI.
Use this if you need to build a voice agent that responds instantly and can be interrupted, while still performing deep thinking or accessing tools behind the scenes.
Not ideal if your application doesn't involve real-time spoken interactions or requires every response to be fully complete before it starts speaking.
Stars
40
Forks
4
Language
Python
License
AGPL-3.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/stimm-ai/stimm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mewmix/nabu
A multi engine TTS & LLM edge computing playground with audio book features and more!
createcandle/voco
Privacy friendly voice control for the Candle Controller / WebThings Gateway, with fully local...
shashank2122/Local-Voice
A real-time, offline voice assistant for Linux and Raspberry Pi. Uses local LLMs (via Ollama),...
botany-labs/voice-ai-js-starter
Starter project for building real-time AI Voice Assistants
lemonadeforlife/nerminal
A simple lightweight & efficient voice assistant built with Python & Vosk.