# asr-mcp

> asr-mcp — fengredrum-asr-mcp. Use this tool when you need to transcribe audio files offline with high accuracy, leveraging Whisper Large V3 and LLM-based correction to generate text, timestamps, and SRT outputs. It solves problems related to speech-to-text transcription, especially in environments with limited internet connectivity. The asr-mcp tool takes in audio files and outputs transcribed text with corresponding timestamps and subtitles.

Canonical page: https://skillsregistry.net/skills/fengredrum-asr-mcp  
JSON: https://api.skillsregistry.net/v1/skills/fengredrum-asr-mcp

## Description

MCP server for local speech-to-text using Whisper Large V3 (MLX), enabling audio transcription with text/timestamps/SRT output and LLM-based correction, all running offline on Apple Silicon.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/dquwe51pit)
- **Repository:** <https://github.com/fengredrum/asr-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": "fengredrum-asr-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/fengredrum-asr-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/fengredrum-asr-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