2.3 KiB
2.3 KiB
Discord Voice Bot (GLaDOS)
Overview
Voice-controlled Discord bot with conversational AI — always available in #coding voice channel
Location
/home/admin/.openclaw/workspace/discord-voice-bot/
Architecture (Completed 2026-02-08)
Components
| Component | Endpoint | Purpose |
|---|---|---|
| TTS | 192.168.0.17:5050 | GLaDOS voice synthesis |
| STT | 192.168.0.17:10300 | Whisper via Wyoming protocol |
| LLM | 192.168.0.17:11434 | Ollama (qwen3-coder-next:cloud) |
| Auto-join | On startup | Joins #coding voice channel |
Voice Pipeline
Wake Word → STT (Whisper) → LLM (Ollama) → TTS (GLaDOS) → Voice Output
Commands
!join— Join voice channel!leave— Leave voice channel!test [text]— Test TTS synthesis!listen— 5-second voice recording (7-10 sec latency)
MCP Integration (OpenClaw Bridge)
MCP Tools Available via Voice
list_projects()— "What am I working on?"create_project(name)— Start new projectadd_task(project, task)— Add tasks via voiceupdate_task_status(taskId, status)— Mark completeget_project_status()— Check overall progress
MCP Server Config
mcp_servers:
- name: "openclaw"
transport: "stdio"
command: "python"
args:
- "C:\Users\admin\.openclaw\workspace\discord-voice-bot\openclaw_mcp_server.py"
Files Created
openclaw_mcp_server.py— FastMCP server exposing OpenClaw toolsmain.py— Bot implementation using discord.py, wyomingconfig.yaml— Configurationrequirements.txt— Dependencies (discord.py, requests, numpy, wyoming)
What Changed (v2)
- Removed GLaDOS direct dependencies (simpler integration)
- Uses existing services (Whisper, Ollama, HTTP TTS)
- Auto-joins voice channel on startup
- Clean async architecture
- MCP bridge for OpenClaw integration
Known Limitations
- Voice latency: 7-10 seconds for
!listen(5s recording + processing) - Not conversational due to latency
- Best for command-based interactions, not real-time chat
Status
✅ COMPLETED — Operational in #coding voice channel
Bot auto-joins on startup and accepts voice commands via MCP bridge.
Status: Complete | Version: 2.0 | Updated: 2026-02-22