Woodstitch — Claude Code MCP server for TTS evaluation
The Woodstitch MCP server for Claude Code sends text-to-speech audio to paid human listeners for blind evaluation. An agent can compare two clips or ask listeners to classify one as human-made or AI-generated.
MIT updated 2026-11-07
claude mcp add tts-human-eval -e WOODSTITCH_API_KEY=<WOODSTITCH_API_KEY> -- uvx woodstitch-mcpWhat Woodstitch does
Woodstitch submits audio for blind review by paid listeners and returns scores with confidence intervals. It supports two study formats: listeners choose between two clips of the same text, or classify a single clip as human or AI speech. MOS, CMOS, MUSHRA and 1–5 rating scales are outside its scope.
The server accepts uploaded local audio or public URLs, prepares a study quote and starts the study after the price is confirmed. It needs a Woodstitch API key, Python 3.10+ and uvx; creating a study can price it without charging, while starting it spends money. A confirmed amount caps the charge, and a higher quote prevents the study from starting.
What it helps with
- compare two speech-synthesis versions of the same passage
- check whether a clip sounds human or AI-generated
- get a study quote before spending money
- export listener ratings as JSON or CSV
Example prompts for the agent
- Compare the spoken quality of
base.wavandcandidate.wav. - Classify
sample.wavas human speech or synthesized speech. - Quote a listening study for
a/001.wavandb/001.wavwithout starting it.
How to install Woodstitch
Platform CLI
claude mcp add tts-human-eval -e WOODSTITCH_API_KEY=<WOODSTITCH_API_KEY> -- uvx woodstitch-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from woodstitch-mcp <command>
Platform CLI
codex mcp add woodstitch --env WOODSTITCH_API_KEY=<WOODSTITCH_API_KEY> -- uvx woodstitch-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from woodstitch-mcp <command>
Config file
{
"mcpServers": {
"woodstitch": {
"command": "uvx",
"args": [
"woodstitch-mcp"
],
"env": {
"WOODSTITCH_API_KEY": "<WOODSTITCH_API_KEY>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from woodstitch-mcp <command>
Config file
{
"servers": {
"woodstitch": {
"type": "stdio",
"command": "uvx",
"args": [
"woodstitch-mcp"
],
"env": {
"WOODSTITCH_API_KEY": "<WOODSTITCH_API_KEY>"
}
}
}
}Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from woodstitch-mcp <command>
Platform CLI
gemini mcp add -e WOODSTITCH_API_KEY=<WOODSTITCH_API_KEY> woodstitch uvx woodstitch-mcpReplace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from woodstitch-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Woodstitch
How do I install Woodstitch in Claude Code?
Set a Woodstitch API key, then run claude mcp add tts-human-eval -e WOODSTITCH_API_KEY=<WOODSTITCH_API_KEY> -- uvx woodstitch-mcp. It requires Python 3.10+ and uvx.
What does Woodstitch do?
It sends TTS audio to paid listeners for blind studies. They either choose between two clips or judge whether one clip is human or AI speech; results can also be exported in JSON or CSV.
What does Woodstitch need to run?
It requires a Woodstitch API key, Python 3.10+ and uvx. Listener studies cost money: creating one gives a quote, and starting it spends funds.