This server gives Claude Code text-to-speech with five engine options. It exposes a speak tool that takes text and optional engine/voice parameters, plus list_voices and get_engine_info for discovery. Works over stdio and includes a Stop hook for auto-speaking responses. The free edge-tts engine ships by default with 400+ neural voices, while paid ElevenLabs and local Kokoro ONNX cover premium and offline cases. Useful if you want hands-free coding feedback or need to audition responses while working in another window. The text safety filter strips code blocks and secrets before speaking, so you get natural language summaries instead of syntax noise.
claude mcp add --transport stdio tomorrow-you-voice-bridge -- npx -y ai-voice-bridge