Live Translate Mcp

waxberry-dev/live-translate-mcp

Adds real-time bilingual speech translation to Claude using a local-first pipeline. Exposes translate_file to process WAV files from disk and translate_speech for base64-encoded audio streams, both handling English and Mandarin Chinese in either direction. Uses Whisper for transcription and Piper for synthesis on your machine, only sending text to Claude's API for the actual translation step. Audio never leaves your device except as translated text. Downloads models automatically on first run and caches them locally. Useful when you need conversational translation tooling integrated directly into Claude Desktop or Claude Code without routing speech through cloud providers. Requires Node 18+, an Anthropic API key, and espeak-ng for phonemisation.

tools: 3
auth: Secret needed
transport: STDIO
env var: 1
last updated: Jun 5, 2026

View on GitHub

Tools

3 tools

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

translate_fileTranslate a WAV audio file. Pass an absolute path — the server transcribes it, translates the text via Claude, synthesises speech, saves `<name>_translated.wav` next to the original, and plays it automatically.

Translate a WAV audio file. Pass an absolute path — the server transcribes it, translates the text via Claude, synthesises speech, saves `<name>_translated.wav` next to the original, and plays it automatically.

No parameter schema in public metadata yet.

translate_speechTranslate raw audio passed as a base64-encoded WAV string. Returns the transcription, translation, and synthesised audio as base64 WAV — useful for programmatic workflows.

Translate raw audio passed as a base64-encoded WAV string. Returns the transcription, translation, and synthesised audio as base64 WAV — useful for programmatic workflows.

No parameter schema in public metadata yet.

health_checkVerify that all dependencies (Whisper model cache, Piper voice files, `espeak-ng`) are present and ready before making a translation request.

Verify that all dependencies (Whisper model cache, Piper voice files, `espeak-ng`) are present and ready before making a translation request.

No parameter schema in public metadata yet.

Configuration

ANTHROPIC_API_KEY*secret

Your Anthropic API key

Readme

Waxberry

live-translate-mcp

Real-time English ↔ Mandarin speech translation for Claude — powered by Whisper, Claude AI, and Piper TTS.

Give Claude the ability to listen, translate, and speak. live-translate-mcp is a Model Context Protocol (MCP) server that adds speech translation as a native tool inside Claude Desktop and Claude Code. Hand it an audio file, and it transcribes, translates, synthesises, and plays the result — entirely on your machine, with Claude handling the translation.

live-translate-mcp demo

What it does

View the full README on GitHub

Details

Repository: github.com/waxberry-dev/live-translate-mcp
Category: Media & Entertainment
Package: live-translate-mcp
Transport: STDIO
Auth: Required
Registry: MCP registry, active

Related Media & Entertainment MCP servers

View all

MiOffice — AI-Powered Workspace Studioio.github.jsvvsolsllc/mioffice125+ browser tools for PDF, Image, Video, Audio, AI, Scanner. Files never leave your device.0stars

Symbols Of Wealth Studiolisleabrahams/symbols-of-wealth-studio-mcpWorld-class creative social media content studio, powered by AI.0stars

PlanPostlukbb/planpost-mcpSchedule posts to 7 social networks, render video and carousels, read analytics and revenue.0stars

TubePullmiketwalker/tubepull-mcpAI YouTube downloader: save YouTube, TikTok, Instagram + 10 more as MP4/MP3 from any AI chat.0stars

Postallpostall-io/postall-mcp-serverPost to 35+ social media platforms. Schedule & publish from Claude AI.0stars

Trezatreza-labs/treza-pluginBuild, run, schedule, and publish AI video pipelines to YouTube and TikTok from any MCP client.0stars