# FreeTTS

Turns assistant text into an MP3 link across 149 languages. Use it to voice responses, search voices, or build spoken scripts.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: freetts
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/freetts/mcp
- Updated: 2026-10-02
- HTML: https://affpapa.org/en/nevibecode/mcp/freetts

## What it does

FreeTTS gives an MCP client a remote speech tool. Text is sent to the service and the assistant receives an MP3 link. The server also exposes voice search, voice suggestions for a language and use case, plus plan and character checks. Its catalogue has 2,253 voices in 149 languages.

The public connection works without an account or key, with standard voices, 2,000 characters per call and per day for each connection, 10 requests a minute, and a short FreeTTS audio tag. Files remain available for one hour. An account key unlocks account-plan features; PRO adds HD and Signature voices, WAV output, longer file retention, dialogue and script tools, and audio transcription.

You can use Streamable HTTP or run the stdio package locally with `npx -y @freetts/mcp`. Local use needs `FREETTS_API_KEY` and Node.js 20 or later. The submitted text goes to FreeTTS and its speech providers, while server logs contain tool, plan, character-count, client, and outcome details rather than the text itself.

## Requirements
- Needs: Node.js (commands run via npx)
- Remote server: `https://mcp.freetts.org/mcp`
- Environment variables: `FREETTS_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

1. **Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://mcp.freetts.org/mcp
```

2. **Platform CLI**
```bash
claude mcp add --env FREETTS_API_KEY=<FREETTS_API_KEY> --transport stdio freetts -- npx -y @freetts/mcp
```
Replace <…> with your own values

### Codex

1. **Platform CLI: remote server**
```bash
codex mcp add freetts --url https://mcp.freetts.org/mcp
```

2. **Platform CLI**
```bash
codex mcp add freetts --env FREETTS_API_KEY=<FREETTS_API_KEY> -- npx -y @freetts/mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "freetts": {
            "url": "https://mcp.freetts.org/mcp"
        }
    }
}
```
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "freetts": {
            "command": "npx",
            "args": [
                "-y",
                "@freetts/mcp"
            ],
            "env": {
                "FREETTS_API_KEY": "<FREETTS_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "freetts": {
            "type": "http",
            "url": "https://mcp.freetts.org/mcp"
        }
    }
}
```
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "freetts": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@freetts/mcp"
            ],
            "env": {
                "FREETTS_API_KEY": "<FREETTS_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

1. **Platform CLI: remote server**
```bash
gemini mcp add -t http freetts https://mcp.freetts.org/mcp
```

2. **Platform CLI**
```bash
gemini mcp add -e FREETTS_API_KEY=<FREETTS_API_KEY> freetts npx -y @freetts/mcp
```
Replace <…> with your own values

## When to use it
- turn assistant replies into MP3 links
- search voices by language or term
- choose a voice for a specific use
- render a multi-speaker dialogue as one file
- transcribe audio from a public URL

## Example prompts
- Turn this reply into spoken English and return the MP3 link.
- Find three voices for a calm German explainer and explain the choices.
- Convert these speaker lines into one audio dialogue with a separate voice for each person.

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16730
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107701
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26673
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23283
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9369
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9298

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md