Supertone TTS MCP Server

A composable MCP toolkit for the Supertone TTS API. Rather than a single "speak this text" command, it exposes Supertone's SDK as a set of building-block tools - synthesis, voice discovery, preview, duration/credit prediction, usage tracking, and full voice-cloning CRUD - that an LLM assembles to fulfill a request. Works in Claude Desktop, Cursor, or any MCP-compatible client. Its 5 documented tools cluster into text, predict, read & search, clone.

People connecting media tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

NO LONGER MAINTAINED

LAST COMMIT 2026-07-23 · ★ 4 · VERIFIED 2026-08-25

Python servers · how we verify → /methodology

01 · Install Supertone TTS

before you install - you'll need

Set SUPERTONE_API_KEY before connecting.

Claude Code

claude mcp add supertone-inc-supertone-mcp -- uvx supertone-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "supertone-inc-supertone-mcp": {
      "command": "uvx",
      "args": [
        "supertone-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

repository archived on GitHub - read-only; no future fixes, security or otherwise

license no standard license detected - usage rights unclear; check the repo before commercial use

pypi package supertone-mcp - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.supertone-inc is GitHub-verified and matches the repo owner

03 · What Supertone TTS can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

An agent gets 5 documented tools across text, predict, read & search, including text_to_speech, predict_duration, search_voice, clone_voice.

Capability map

Tools grouped from the project's README - what Supertone TTS lets an agent do.

Text

1 tool - e.g. Text To Speech

text_to_speech

Predict

1 tool - e.g. Same core parameter schema as text_to_speech (long text auto-chunked). Returns "Predicted duration: 2.34s (credit usage is proportional to duration).".

predict_duration

read & search

1 tool - e.g. All parameters optional. With no filters → full catalog. With any filter → first response line is Filters applied: ....

search_voice

Clone

1 tool - e.g. Clone Voice

clone_voice

Merge

1 tool - e.g. Merge Audio Files

merge_audio_files

Latest releases

v0.3.1 · 2026-06-17

Bug-fix release for merge_audio_files (reported against 0.3.0). Published to PyPI (supertone-mcp==0.3.1) and the MCP Registry. · Fixed · WAV merge Duration mis-reported (#52 / ISSUE-032). ffmpeg rendered to a…

v0.3.0 · 2026-06-17

Audio-assembly milestone: the toolkit can stitch its own text_to_speech outputs into a single deliverable. Published to PyPI (supertone-mcp==0.3.0) and the MCP Registry. · > Backfilled release record (the tag and PyPI…

v0.2.0 · 2026-06-05

04 · Who maintains Supertone TTS

Supertone TTS is maintained by supertone-inc. It's the only MCP server we track from this author; the repo dates to Mar 2026.

05 · Facts

repository: github.com/supertone-inc/supertone-mcp
category: media - dead as of 2026-08-25.
release cadence: 5 releases in the last 90 days (latest 2026-06-17)
registry: io.github.supertone-inc/supertone-mcp (active, first published 2026-05-27 · 4 versions)
packages: pypi:supertone-mcp

06 · Supertone TTS FAQ

Is Supertone TTS still maintained?

Its last commit was 2026-07-23 (as of 2026-08-25) - we classify it as dead.

What can Supertone TTS do?

An agent gets 5 documented tools across text, predict, read & search, including text_to_speech, predict_duration, search_voice, clone_voice.

How do I install Supertone TTS?

Run `uvx supertone-mcp`. The README documents one environment variable (SUPERTONE_API_KEY) to set first. Set SUPERTONE_API_KEY before connecting. You can also paste the ready-made client config above.

Does Supertone TTS run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Supertone TTS

Alternatives to Supertone TTS

Maintained media servers if Supertone TTS isn't the fit.