Text to Speech

Give your AI assistant a voice — locally, with no API key, no account, and no cloud service.

Text to Speech is an open-source Model Context Protocol (MCP) server that lets AI assistants read text aloud on the user's computer. It uses the speech synthesizer already present on the host operating system, so nothing you ask it to say ever leaves your machine.

Runs onWindows, macOS, and Linux. Install is one line:

The server exposes one model-controlled tool:

Use it for user-provided text, assistant answers, accessibility workflows, or spoken progress updates while an agent works.

Most text-to-speech MCP servers wrap a cloud API, which means an account, a key, per-character billing, and your text leaving the machine. This one uses the speech engine your operating system already ships, so it works offline, costs nothing, and keeps text local — which matters if you work anywhere that regulates where data may go.

It also ships anagent narration skill, so an assistant knowshowto narrate, not just that it can.

command = "uvx" args = ["text-to-speech-mcp"] startup_timeout_sec = 30 tool_timeout_sec = 300 enabled = true

Some clients use TOML, JSON, or a graphical settings page. Useuvx text-to-speech-mcpas the server command and restart the client after changing its configuration.

git clone https://github.com/Engr-FaizanAli/text-to-speech-mcp.git cd text-to-speech-mcp python -m pip install .

Then configure the client to runtext-to-speech-mcpdirectly.

Use the Text to Speech tool to read aloud: The deployment completed successfully.

Use the Text to Speech tool to read your final response aloud before displaying it.

Read visible intermediate progress updates in order:

Use the text_to_speech MCP server's speak_text tool for spoken progress updates. For every meaningful intermediate update that you display to me: 1. Call speak_text with the exact update text you are about to display. 2. Wait for the call to finish before producing or speaking the next update. 3. Then display the same update in text. Also call speak_text with the exact final answer before displaying it. Never narrate hidden reasoning, chain-of-thought, secrets, credentials, raw tool output, terminal logs, or source code unless I explicitly ask you to read that content aloud. Do not invoke speech calls in parallel. If the tool is unavailable, continue normally in text and report the failure once.

Thetext_to_speechportion is an example client-side server name. Clients may display a different namespace while keeping the tool namespeak_text.

The tool is model-controlled under MCP. The user decides when to ask the model to call it, and the MCP client may show or require approval for tool calls.

With any of the built-in backends, text is passed from the MCP client to a local Python process and then to the operating system's speech components. It is not sent to this project, an external API, or a cloud TTS provider. Generated WAV files are written to atext-to-speech-mcpdirectory inside the system temporary directory (%TEMP%on Windows,/tmpon macOS and Linux) and deleted after playback unlessTEXT_TO_SPEECH_KEEP_AUDIO=trueis set.

Thehttpbackend is the exception: whether text leaves the machine depends entirely on the endpoint you configure.

Do not ask an AI assistant to speak secrets, credentials, private keys, hidden reasoning, or sensitive tool output.

The default requires no configuration.TEXT_TO_SPEECH_BACKENDis unset and the server selectssapi,say, orespeakto match the host platform.

To pin one explicitly, or to use a backend that is not built into the OS, setTEXT_TO_SPEECH_BACKENDtosapi,say,espeak,piper,transformers_mms, orhttp. The last three require their own local model, binary, Python dependencies, or endpoint.TEXT_TO_SPEECH_FALLBACK_BACKENDnames a second backend to try if the first fails. Seebackend configuration.

skills/project-tts-responder/SKILL.mdis a ready-made narration policy built onspeak_text. Copy it into your project's.claude/skills/directory:

A server for text-to-speech (TTS) using the VoiceVox engine.