Skip to main content
MCP server CX Codex

Text to Speech — 20+ Languages, MP3 Output — Claude Code MCP server

Text to Speech — 20+ Languages, MP3 Output is a Claude Code MCP server that converts text into speech in 20+ languages and returns base64 MP3 audio for voice alerts and spoken UI.

no license 2,769 installs updated 2026-04-13

Install into Claude Code · Platform CLI: remote server All methods and platforms ↓
claude mcp add --transport http text-to-speech https://text-to-speech--axel-belfort.run.tools
Open on GitHub

What Text to Speech — 20+ Languages, MP3 Output does

The server provides a single tool, media_text_to_speech. It sends your prompt to the Google TTS engine and responds with a JSON payload holding base64-encoded MP3 audio. Alongside the sound stream, the tool delivers the character count, the language code, and an estimated duration.

Speech synthesis works across more than 20 languages. You do not need a traditional API key, but each call triggers a $0.005 micropayment via x402 on Base L2.

What it helps with

  • generate MP3 voice clips across 20+ languages
  • play voice notifications directly inside agent workflows
  • build spoken responses for accessibility features

Example prompts for the agent

  • Convert this greeting into spoken audio using media_text_to_speech
  • Generate speech audio for this warning message in Spanish

How to install Text to Speech — 20+ Languages, MP3 Output

Platform CLI: remote server

claude mcp add --transport http text-to-speech https://text-to-speech--axel-belfort.run.tools

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about Text to Speech — 20+ Languages, MP3 Output

How to install Text to Speech — 20+ Languages, MP3 Output in Claude Code?

Run claude mcp add --transport http text-to-speech https://text-to-speech--axel-belfort.run.tools in your terminal.

What does this MCP server do?

It converts text into speech across 20+ languages with Google TTS, returning base64-encoded MP3 audio along with duration details.

Is an API key required for voice synthesis?

No API key is needed. Each request settles via x402 micropayments at $0.005 per call on Base L2.

Similar MCP servers

All MCP servers for AI and ML →

Project sponsors

Companies that keep this analytics open