# MCP Audio RAG Server

> Use this tool when you need to transcribe audio files and create a searchable knowledge base from meetings, podcasts, lectures, and other recordings. It solves the problem of extracting valuable information from audio content by using Google Gemini AI to generate accurate transcripts. The tool takes audio files as input and outputs a searchable database that allows users to ask natural language questions about the content.

Canonical page: https://skillsregistry.net/skills/matheusslg-mcp-audio-rag  
JSON: https://api.skillsregistry.net/v1/skills/matheusslg-mcp-audio-rag

## Description

Enables transcription of audio files using Google Gemini AI and creates a searchable knowledge base, allowing users to ask natural language questions about content in meetings, podcasts, lectures, and other audio recordings.

## Trust

- **Trust score (0–1):** 0.94
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/knyus8948d)
- **Repository:** <https://github.com/matheusslg/mcp-audio-rag>

## 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": "matheusslg-mcp-audio-rag"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/matheusslg-mcp-audio-rag` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/matheusslg-mcp-audio-rag/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