Back to code-only MCP servers

speech-mine

updated this year

Working towards an MCP setup that allows humans to format audio with an agent in the loop. Useful for repetitive audio formatting tasks where the content is well defined.

Code-only MCP server: no hosted endpoint, so you install and run it yourself. It is not probed, graded or counted in our reachability statistics.

Get it

Repository
github.com/WISCLab/speech-mine
License
MIT
Last update
2026-04-22
GitHub stars
★ 1
Homepage
wisclab.github.io/speech-mine/

Listed in

Run this server as a hosted endpoint? Submit the endpoint and it moves to the remote directory, where it is probed and graded.