Overview

AI-generated overview

Lets an assistant turn text into speech and return an MP3 link, with voice listing and script-to-audio tools.

What it does: FreeTTS exposes text-to-speech tools over a remote MCP endpoint. text_to_speech converts text into an MP3 link using voices across 149 languages, while list_voices and suggest_voice help pick a voice and check_usage reports plan and remaining characters. Account-gated tools add dialogue_to_speech for multi-speaker scripts, script_to_tracks for timed script mode, and transcribe_audio for turning a public audio URL into text.
When to use it: Useful when an assistant should read text aloud, generate narration or voiceovers, produce multi-speaker dialogue audio, or transcribe a public audio link. It fits chat, coding, and writing clients that support remote MCP servers and need speech output without local audio tooling.
Requirements: A remote Streamable HTTP endpoint; nothing to install. Free tools need no account or key. Account tools require a FreeTTS account, and PRO tools require a PRO plan; a key can be supplied as an Authorization Bearer header or an x-api-key header, or through the OAuth sign-in flow. Network access to the FreeTTS service is required.

Before you install

Text sent for speech is passed to FreeTTS and its speech providers under the FreeTTS privacy policy, and keyless calls are metered by IP address. Account and PRO tools need a FreeTTS API key, which is a credential; deleting it in the dashboard disconnects assistants that used it. Free output includes a spoken FreeTTS tag and files are kept briefly, so check plan limits before relying on it.

Installation

In SourceWeft

Open FreeTTS in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Other MCP clients

Add this to your client's mcpServers config.

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

README

FreeTTS MCP server

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

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

What it does

Tool	What it does	Needs
`text_to_speech`	Text in, MP3 link out. 2,253 voices in 149 languages.	Nothing. Free without an account.
`list_voices`	Voices for a language or search word, with ids.	Nothing
`suggest_voice`	Three voices for a language and a use, with reasons.	Nothing
`check_usage`	Plan and characters left.	Nothing
`dialogue_to_speech`	`Name: line` script, a voice per speaker, one file.	A FreeTTS account (PRO for the full feature)
`script_to_tracks`	Script mode: exact `(pause 2)`, `(beep)`, `(ding)`, `TRACK:` files, `CUE:` voice, scenes.	FreeTTS PRO
`transcribe_audio`	A 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

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:

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

Codex CLI and ChatGPT desktop

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

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

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 buildPUBLIC_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

npm ci && npm run buildPUBLIC_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.

Source: README.md at commit 23b2a79

Tools

0

Tool metadata has not been indexed yet.

Version history

1

v1.0.1LatestSep 30, 2026

FreeTTS