MCERQUA/OpenVoiceUI

Open voice UI shell for AI agents. Bring any LLM, TTS, or framework — handles voice I/O, Agent driven web canvas, music, and agent profiles.

51
/ 100
Established

Renders live HTML canvas mid-conversation via server-sent events and iframe isolation, enabling real-time web app generation rather than text responses. Includes 35+ extensible skills, parallel sub-agent delegation, multi-provider LLM/STT/TTS adapters, and persistent memory across sessions. Built on Python/Flask backend with vanilla JS frontend, supporting Ollama, Deepgram, ElevenLabs, and 20+ other integrations for fully self-hosted deployment.

Available on npm.

No Dependents
Maintenance 13 / 25
Adoption 5 / 25
Maturity 18 / 25
Community 15 / 25

How are scores calculated?

Stars

9

Forks

5

Language

JavaScript

License

MIT

Category

voice-ai-agents

Last pushed

Mar 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/MCERQUA/OpenVoiceUI"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.