Voice Analyser - retired

This project is no longer maintained.

Voice Analyser extracted a writing voice from published articles and generated a Claude Skill from it - measuring the statistical fingerprint of how someone writes (sentence rhythm, vocabulary, argument flow) and teaching the model by example rather than by rule.

It was always flagged experimental, and it stays interesting, but it is not something we are keeping current. Rather than leave a half-tended tool in the set pretending otherwise, we are retiring it.

What this means for you

• The npm package still installs. @houtini/voice-analyser is deprecated, not unpublished. Nothing you have running will break.

• This repository is archived. The code stays readable and every existing link keeps working, but there are no further releases, and issues and pull requests are closed.

• The skills it generated are yours. They are plain files on your disk and keep working regardless of what happens here.

Related MCP server: loreto-mcp

If you want to carry on with it

The approach is sound and the code is MIT. Fork it. The core idea - measure real samples and teach by example instead of writing a style guide full of rules - holds up well, and it is the same principle behind the voice skills we still use day to day.

The rest of the set

The maintained Houtini MCP servers are listed at github.com/houtini-ai.

Part of the Houtini open-source MCP set. Questions: hello@houtini.com.