Discord Voice AI – Self-hosted bot that talks in voice channels
Voice-in/voice-out Discord bot on free-tier Groq and Google APIs, self-hosted.
The repo actually solves the messy plumbing of live voice agents: modular ASR→LLM→TTS adapters plus an optional PersonaPlex speech-to-speech path, per-agent env overrides, and a Playwright-driven Jitsi bot for room joining. It's a useful MVP for anyone prototyping AI co-hosts, though mixing backends is still manual and PersonaPlex demands extra infra, so it's more pragmatic experiment than turnkey product.
Developers and ML engineers building audio bots/co-hosts for live events, community room operators, and researchers prototyping multi-agent voice systems
Voice-in/voice-out Discord bot on free-tier Groq and Google APIs, self-hosted.
Multi-speaker voice model with natural interruption and barge-in prevention, genuinely different from turn-taking chatbots.
Agents trigger events, program controls state—inverts the usual orchestration model.
Voice-controlled agent orchestration in a sea of similar multi-agent tools.
Shared state for AI agents that actually prevents duplicate work and token waste.
Full voice agent (STT→LLM→TTS) runs locally on GPU, no backend needed.