# io.github.jwulff/whisper-mcp

> Use this tool when you need to transcribe local audio files into text using OpenAI Whisper models. It solves problems of manual transcription and speech-to-text conversion, providing accurate and efficient transcription capabilities. The tool takes in audio files as input and outputs transcribed text, ideal for use cases such as podcast transcription, voice note conversion, or audio data analysis.

Canonical page: https://skillsregistry.net/skills/io-github-jwulff-whisper-mcp  
JSON: https://api.skillsregistry.net/v1/skills/io-github-jwulff-whisper-mcp

## Description

Local audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 0.1.1
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.jwulff%2Fwhisper-mcp)
- **Repository:** <https://github.com/jwulff/whisper-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "io-github-jwulff-whisper-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-jwulff-whisper-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-jwulff-whisper-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt