ditto.audio

audio.dittov1.2.0Updated Oct 7, 2026

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

VerifiedStreamable HTTPWeb executableMedia & Design

Overview

AI-generated overview

Lets an assistant browse ditto.audio voices and turn text into speech, returning short-lived download links.

What it does
Connects an assistant to the ditto.audio text-to-speech service. Tools include list_voices for the voice catalogue plus custom voices, list_languages for language codes and engines, and text_to_speech, which synthesizes text and returns a download URL (MP3 by default, with FLAC, WAV and others on request). Batch tools queue up to 1000 texts, report progress, return result URLs, and cancel a batch while keeping finished audio.
When to use it
Useful when an assistant needs to produce spoken audio from text, such as narration, voiceovers, or reading content aloud, and when larger volumes of text should be synthesized as a batch rather than one item at a time.
Requirements
A remote Streamable HTTP endpoint at no local package or runtime. A ditto.audio account is needed: clients sign in with OAuth on first connect, or headless use sends an API key as the Authorization header. Network access is required.
Before you install
The optional Authorization header carries a ditto.audio API key for headless use; treat it as a secret. Connections draw on the account's monthly allowance, so usage may be metered or billed. Synthesis sends the supplied text to ditto.audio, and generated audio is returned as short-lived download links rather than inline bytes.

Installation

In SourceWeft

  1. Open ditto.audio in the dashboard and add it to a workspace.
  2. 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": {
    "tts": {
      "type": "http",
      "url": "https://mcp.ditto.audio"
    }
  }
}

README

ditto.audio MCP server

Text-to-speech for AI agents. Connect ditto.audio to Claude, ChatGPT, Cursor, VS Code, Codex or any Model Context Protocol client. Your agent can then browse voices and synthesize speech that comes back as short-lived download links, never as audio bytes in the chat.

Endpoint: https://mcp.ditto.audio (Streamable HTTP)

You sign in with your ditto.audio account the first time your client connects. There is no key to paste. Each connection appears under Account -> API keys as a connected app, draws on the same monthly allowance as your keys, and can be disconnected there.

Install

ClientHow
Claude (web, desktop, mobile, and Claude Code signed in with a Claude plan)Add to Claude, then Connect and sign in
CursorAdd to Cursor
VS CodeInstall in VS Code
Claude Code (API key or Console login)claude mcp add --transport http --scope user ditto https://mcp.ditto.audio, then /mcp -> Authenticate
Claude Code (plugin)/plugin marketplace add ditto-audio/ditto-mcp then /plugin install ditto@ditto-audio
ChatGPTSettings -> Security and login -> Developer mode on, then chatgpt.com/plugins -> + -> https://mcp.ditto.audio
Codexcodex mcp add ditto --url https://mcp.ditto.audio then codex mcp login ditto

Headless (CI, servers): skip the sign-in and send an API key from your API keys page as Authorization: Bearer ditto_sk_live_....

Tools

ToolWhat it does
list_voicesBrowse the voice catalogue plus your own custom voices
list_languagesEvery language code and which engines speak it
text_to_speechSynthesize text and get a download URL (MP3 by default; FLAC/WAV and more on request)
create_speech_batchQueue up to 1000 texts at once
get_speech_batchProgress of a batch
get_speech_batch_resultsDownload URLs for a batch's items
cancel_speech_batchStop a batch; finished items keep their audio

Full reference, generated from the live server: https://ditto.audio/docs/mcp

What is in this repository

PathFor
server.jsonThe official MCP Registry entry (audio.ditto/tts)
.claude-plugin/marketplace.json, plugins/ditto/Claude Code plugin marketplace
.cursor-plugin/plugin.json, mcp.jsonCursor Marketplace plugin

Support

Email [email protected] or see ditto.audio/support. Using the server is subject to the terms and the privacy policy.

Copyright (c) 2026 ditto.audio. All rights reserved (see LICENSE).

Source: README.md at commit 7060b50

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.2.0LatestOct 7, 2026