# ditto.audio [Health: Active]

**Category:** 🎧 Text-to-Speech  
**Repository:** https://github.com/ditto-audio/ditto-mcp  
**GitHub Stars:** 0  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/ditto-audio

## Description
Text-to-speech: browse voices and synthesize natural speech from text with ditto.audio.

## Tools
Capabilities this server exposes over MCP:

- **list_voices** — Browse the voice catalogue plus your own custom voices
- **list_languages** — Every language code and which engines speak it
- **text_to_speech** — Synthesize text and get a download URL (MP3 by default; FLAC/WAV and more on request)
- **create_speech_batch** — Queue up to 1000 texts at once
- **get_speech_batch** — Progress of a batch
- **get_speech_batch_results** — Download URLs for a batch's items
- **cancel_speech_batch** — Stop a batch; finished items keep their audio

## Claude Desktop Quick Installation
Remote MCP endpoint (confidence: high). Install path detected from listing signals. Add as a URL/SSE server in your client:

```json
"mcpServers": {
  "ditto-audio": {
    "url": "https://mcp.ditto.audio"
  }
}
```

## Documentation

## What ditto.audio MCP server does

The ditto.audio MCP server gives MCP-compatible AI clients access to ditto.audio's text-to-speech service. Agents can inspect the available voice catalogue, including custom voices associated with the connected account, and check which speech engines support particular language codes.

Speech generation is available for both individual texts and larger jobs. A single request returns a temporary download URL for the generated audio. MP3 is the default output, while FLAC, WAV, and other formats can be requested. For repeated or high-volume work, the server can queue up to 1,000 texts in one batch.

## How it works

The service is hosted at `https://mcp.ditto.audio` and uses Streamable HTTP. A supported client connects to that endpoint and authenticates with a ditto.audio account on the first connection. Connected applications appear in the account's API keys area, use the account's monthly allowance, and can be disconnected there.

The batch workflow is split across separate tools. After creating a batch, an agent can query its progress, retrieve download URLs for completed items, or cancel the batch. Cancelling does not remove audio items that have already finished.

For unattended environments such as CI or servers, authentication can use a ditto.audio API key in an `Authorization: Bearer` header instead of an interactive sign-in. The README does not specify an environment variable for that key.

## Setup and configuration

Client-specific installation options are provided for Claude, Cursor, VS Code, Claude Code, ChatGPT, and Codex. Claude Code can connect with an HTTP MCP command or through the published Claude Code plugin. Cursor and VS Code provide installation links, while Codex uses its MCP add and login commands. ChatGPT requires Developer mode before adding the endpoint.

Interactive connections use account sign-in. Headless connections require an API key from the ditto.audio API keys page and must send it as a bearer token. The repository also includes registry and marketplace metadata for the server, including Claude Code and Cursor plugin files.

## Tools and capabilities

The ditto.audio MCP server exposes these tools:

- `list_voices` finds catalogue voices and the account's custom voices.
- `list_languages` returns language codes and the engines that support them.
- `text_to_speech` converts text to speech and returns a download URL.
- `create_speech_batch` queues as many as 1,000 text items.
- `get_speech_batch` reports batch progress.
- `get_speech_batch_results` returns download URLs for batch items.
- `cancel_speech_batch` stops a batch while preserving completed items.

## Limitations and notes

Generated audio is provided through short-lived download links, not as audio bytes inside the chat. Usage draws from the same monthly allowance as the account's API keys. The service requires either an authenticated ditto.audio account connection or a valid API key for headless use.

The repository states that use is subject to ditto.audio's terms and privacy policy. It directs support requests to ditto.audio support or the listed support email.

_Full upstream README: https://allmcps.com/mcp/ditto-audio/readme_