About Speech MCP
Speech MCP is an MCP server in the AI category: unified STT/TTS MCP server — WhisperX transcription + Qwen3 TTS, record/transcribe/speak tools.
The repository has 1 stars and 0 forks.
Install
git clone https://github.com/sandraschi/speech-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
Ask AI about Speech MCP
Powered by Claude · Grounded in docs
Security checks
- ✓README presentThe repository ships documentation.
5 checks have not been run yet.
README
Speech-MCP
A modern multi-provider speech gateway featuring Gemini Live real-time voice chat, Gemini 3.1 Flash TTS, Hume AI Octave, and ElevenLabs voice cloning.
The Dual-Core Experience
MCP Server — Advanced speech, RAG, and state management for agents and IDEs (Claude Desktop, Cursor, Windsurf).
Modern Webapp — A browser-based cockpit for real-time voice conversations, Creative Labs polyglot synthesis, voice clone management, and system monitoring.
Providers
| Provider | Mode | Quality | Key |
|---|---|---|---|
gemini_live |
Real-time conversation | Very good | GOOGLE_API_KEY |
gemini |
Batch TTS | Highest | GOOGLE_API_KEY |
gemma |
Batch TTS/STT | SOTA Local | None |
hume |
Batch TTS (Octave) | High | HUME_API_KEY |
elevenlabs |
Batch TTS + voice cloning | High | ELEVENLABS_API_KEY |
windows |
Batch TTS (SAPI5) | Low | None |
Key Features
Gemma 4 Native Multimodal — SOTA 2026 local engine integration. Features native audio/vision encoders for low-latency conversational reasoning. Supports prosody-aware interaction and local-first Zero-STT fallback. Optimized for A4B throughput (100+ t/s).
Gemini 3.1 Flash TTS — Highest-quality cloud synthesis (gemini-3.1-flash-tts-preview). 31 prebuilt voices, 100+ languages, expressive audio tags ([whispers], [excited], etc.).
Creative Labs — Polyglot synthesis demo with 19 languages (European, Slavic, Classical, Experimental, Global), literary samples, voice selection, prosody slider, and tongue-twister panel.
Voice Cloning — ElevenLabs Instant Voice Clone (IVC) via file upload. 5-second minimum audio sample. Cloned voices appear in the voice library immediately.
Offline Wake-Word — Privacy-first detection using openWakeWord (fully offline, Apache 2.0, no API key).
RAG / Semantic Search — LanceDB + FastEmbed knowledge base over project docs. ask_docs tool uses Claude sampling for grounded Q&A.
Local AI — Ollama and LM Studio model discovery and grounded generation.
Documentation
- Installation
- Configuration reference
- Local voice alternatives ← kyutai-mcp / offline
- Gemini Live voice chat ← new
- Architecture
- openWakeWord
- Yahboom robot integration
- RAG technical overview
- Modern speech AI
Quick Start
# Clone and install
git clone https://github.com/sandraschi/speech-mcp
cd speech-mcp
uv sync
# Configure keys
cp .env.example .env
# Edit .env — add GOOGLE_API_KEY at minimum
# Start backend
uv run python -m speech_mcp.webapp
# Start frontend (separate terminal)
cd web && npm install && npm run dev
Backend: http://localhost:10918 — Frontend: http://localhost:10917
For Claude Desktop MCP integration see docs/configuration.md.
License
MIT — see LICENSE.
Contributors: @sandraschi. PRs welcome.
README copy captured when this server was indexed; it may lag the repository. The original is authoritative.