Voice Bridge

tomorrow-you/voice-bridge

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.

tools: 4
transport: STDIO
last updated: Apr 29, 2026

View on GitHub

Tools

4 tools

Public tool metadata for what this MCP can expose to an agent.

speakSpeak text aloud. Optionally override engine for this call.

Speak text aloud. Optionally override engine for this call.

No parameter schema in public metadata yet.

set_engineSwitch the default TTS engine (`auto`, `edge-tts`, `elevenlabs`, `kokoro`, `say`, `espeak`)

Switch the default TTS engine (`auto`, `edge-tts`, `elevenlabs`, `kokoro`, `say`, `espeak`)

No parameter schema in public metadata yet.

get_statusShow current mode, engine, and available engines

Show current mode, engine, and available engines

No parameter schema in public metadata yet.

list_voicesList available voices. Defaults to current engine if omitted.

List available voices. Defaults to current engine if omitted.

No parameter schema in public metadata yet.

Readme

Voice Bridge

Multi-engine text-to-speech for AI coding assistants. Speaks responses aloud from Claude Code, Cursor, or VS Code via a Claude Code plugin, MCP server, or CLI pipe.

pip install ai-voice-bridge[edge]   # Install with free edge-tts engine
voice-bridge test                   # Verify audio output
voice-bridge on                     # Enable always-on mode (optional)

Features

Free by default -- edge-tts uses Microsoft Neural voices, no API key needed
5 engines -- edge-tts, ElevenLabs, Kokoro (local ONNX), macOS say, espeak-ng
Text safety filter -- strips code blocks, secrets, file paths, URLs, and markdown before speaking
Claude Code plugin -- Stop hook speaks responses automatically, MCP server for tool-based control
Voice discovery -- browse, filter by gender/locale, and preview voices interactively

Prerequisites

View the full README on GitHub

Details

Repository: github.com/tomorrow-you/voice-bridge
Category: Media & Entertainment
Package: ai-voice-bridge
Transport: STDIO
Registry: MCP registry, active

Related Media & Entertainment MCP servers

View all

FunASRmodelscope/funasrTranscribe local audio with FunASR and SenseVoice using private, on-device inference.21Kstars

Remove AI Watermarkswiltodelta/remove-ai-watermarksIdentify and clean AI watermarks and provenance in your own images, video, and text.6.4Kstars

WhatsApplharries/whatsapp-mcpExposes a MCP server to search, read, and send WhatsApp messages and media via Claude5.6Kstars

Remocn: Remotion MCP serverremocn/remocnHosted MCP for Remotion videos: search Remocn components, read docs, plan a video, preview it.1.7Kstars

Meta Adspipeboard-co/meta-ads-mcpProvides an MCP server to analyze, manage, and optimize Meta Ads campaigns via AI across Facebook, Instagram, and Meta platforms.908stars

XActionsnirholas/xactionsX/Twitter automation MCP: scrape, post, schedule, analyze, engage. No API key required.644stars