modal-labs/quillman
A voice chat app
Implements bidirectional WebSocket streaming with Kyutai Lab's Moshi speech-to-speech model, using the Mimi streaming codec and Opus compression to achieve near-instantaneous response times. Built as a Modal serverless application with a FastAPI backend exposing the Moshi inference server and a React frontend, designed as a reference implementation for speech-based language model applications.
1,198 stars. No commits in the last 6 months.
Stars
1,198
Forks
155
Language
Python
License
MIT
Category
Last pushed
May 21, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/modal-labs/quillman"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
rapidaai/voice-ai
Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time...
ArchishmanSengupta/autovoiceevals
A self-improving loop for voice AI agents. Uses karpathy's autoresearch as foundation.
lixiangyu890601/EasyAICC-Easy-AI-Call-Center
外呼系统，智能外呼，自动外呼系统，人工外呼，呼叫中心
voicetestdev/voicetest
Test harness for voice agents. Import from Retell, VAPI, Bland, LiveKit. Run autonomous...
jordicor/santa-claus-is-calling
A magical Christmas experience where Santa Claus (AI with Santa's voice) actually calls children...