# SpeakToMe MCP

> Use this tool when you need to transcribe spoken audio into text in real-time, solving problems such as converting voice notes to written text or enabling voice-controlled applications. It takes microphone audio as input and returns transcripts as output, utilizing local faster-whisper transcription for efficient processing. Ideal for use cases where internet connectivity is limited or speedy transcription is crucial, such as in voice assistants, meeting note-takers, or accessibility tools.

Canonical page: https://skillsregistry.net/skills/alma3lol-speaktomemcp  
JSON: https://api.skillsregistry.net/v1/skills/alma3lol-speaktomemcp

## Description

A local MCP server for Linux that records microphone audio and returns transcripts using local faster-whisper transcription.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/f4tvb79sac)
- **Repository:** <https://github.com/alma3lol/SpeakToMeMCP>

## 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": "alma3lol-speaktomemcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/alma3lol-speaktomemcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/alma3lol-speaktomemcp/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