FreeTTS MCP server

MCP serverMedia

Text to speech in 149 languages: MP3 links from any assistant. Free without an account.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use FreeTTS MCP server to list voices

Install FreeTTS MCP server

The server’s own address, for the clients that take one directly. Or connect ahel once and every client you use reads it from one address, with the account kept on ahel rather than in each client’s config.

  • Claude Code

    claude mcp add --transport http --scope user freetts-mcp-server 'https://mcp.freetts.org/mcp'

    Run it once in your project, then open /mcp to approve any sign-in the server asks for.

  • Claude Desktop

    https://mcp.freetts.org/mcp

    Add a custom connector in Settings, paste this address, and approve the sign-in.

  • Cursor

    cursor://anysphere.cursor-deeplink/mcp/install?name=freetts-mcp-server&config=eyJ1cmwiOiJodHRwczovL21jcC5mcmVldHRzLm9yZy9tY3AifQ==

    Open the link and Cursor adds the server at that address.

  • ChatGPT

    https://mcp.freetts.org/mcp

    In Settings, enable Developer mode, create an MCP app, and paste this address. Your plan and workspace must allow custom apps.

  • Codex

    codex mcp add freetts-mcp-server --url 'https://mcp.freetts.org/mcp'

    Run it once, then sign in with codex mcp login freetts-mcp-server if the server asks for an account.

From the project's README

As published by freetts/mcp in README.md.

Text to speech inside Claude, ChatGPT, Cursor, VS Code, Codex, Windsurf, Gemini CLI and any other MCP client. One remote server, nothing to install:

https://mcp.freetts.org/mcp

Ask your assistant to read something aloud, and it calls FreeTTS and hands you an MP3 link.

What it does

ToolWhat it doesNeeds
text_to_speechText in, MP3 link out. 2,253 voices in 149 languages.Nothing. Free without an account.
list_voicesVoices for a language or search word, with ids.Nothing
suggest_voiceThree voices for a language and a use, with reasons.Nothing
check_usagePlan and characters left.Nothing
dialogue_to_speechName: line script, a voice per speaker, one file.A FreeTTS account (PRO for the full feature)
script_to_tracksScript mode: exact (pause 2), (beep), (ding), TRACK: files, CUE: voice, scenes.FreeTTS PRO
transcribe_audioA public audio URL in, text out.A FreeTTS account

Free without a key: standard voices, 2,000 characters a call and a day per connection, 10 requests a minute, a short spoken "FreeTTS" tag at the end, files kept one hour.

With a FreeTTS key (free account or PRO): the account's plan. PRO: HD and Signature voices, no tag, 10,000 characters a call, 1,000,000 a month, WAV, files kept 30 days, dialogue and Script mode tools. Keys: freetts.org/dashboard (API keys).

Add it to your client

Claude Code

claude mcp add --transport http freetts https://mcp.freetts.org/mcp

With a key: add --header "Authorization: Bearer ft_live_...", or run /mcp inside a session to connect with the sign-in flow.

Claude (web, desktop, mobile): Settings, Connectors, Add custom connector, paste https://mcp.freetts.org/mcp. Free tools work at once; when a tool needs your account Claude shows Connect.

Cursor: Install in Cursor, or in ~/.cursor/mcp.json:

{ "mcpServers": { "freetts": { "url": "https://mcp.freetts.org/mcp" } } }

VS Code: Install in VS Code, or in .vscode/mcp.json:

{ "servers": { "freetts": { "type": "http", "url": "https://mcp.freetts.org/mcp" } } }

Codex CLI and ChatGPT desktop

codex mcp add freetts --url https://mcp.freetts.org/mcp

ChatGPT (web): Settings, Apps (Developer Mode), add https://mcp.freetts.org/mcp.

Windsurf, ~/.codeium/windsurf/mcp_config.json:

{ "mcpServers": { "freetts": { "serverUrl": "https://mcp.freetts.org/mcp" } } }

Any other client: use https://mcp.freetts.org/mcp as the server URL (Streamable HTTP). To use your account without the sign-in flow, send your key as Authorization: Bearer ft_live_... or x-api-key: ft_live_....

Full guide with copy buttons: freetts.org/developers/mcp.

Sign-in (OAuth)

The server is an OAuth 2.1 authorization server (PKCE, dynamic client registration, client ID metadata documents, RFC 9728 and 8414 metadata). Free tools need no sign-in. When a client calls a tool that needs your account, the server answers 401 and the client shows its Connect flow; the page asks for a FreeTTS API key from your dashboard and binds the connection to it. Delete the key in the dashboard to disconnect every assistant that used it.

Privacy

The text you send is sent to FreeTTS and its speech providers exactly as from the website, under the FreeTTS privacy policy. Calls without a key are metered by the caller's IP address. The server logs tool name, plan, character count, client name and outcome, never the text.

Running it yourself

npm ci && npm run build
PUBLIC_URL=https://mcp.example.com FASTAPI_URL=http://127.0.0.1:8042 FREETTS_SERVICE_API_KEY=ft_live_... MCP_JWT_SECRET=... node dist/index.js

It expects a FreeTTS API server behind FASTAPI_URL; the public one is not reachable that way, so this is for FreeTTS itself. The code is here so you can read what the server does.

License: MIT.

Tools it offers (7)

What this server listed when ahel dialed its public endpoint in Oct 2026, with no key and no account of yours. The names are the server’s own.

  • list_voices
  • suggest_voice
  • text_to_speech
  • check_usage
  • dialogue_to_speech
  • script_to_tracks
  • transcribe_audio

Signals

Last commit
Sep 2026
Advanced
Delivery
FreeTTS MCP server → your ahel connector (mcp.ahel.ai) → your AI.
Item type
mcp-server
Key
org-freetts-mcp
Source
github.com/freetts/mcp
Hosted endpoint
https://mcp.freetts.org/mcp