# speechtotext

> speechtotext — sssamuelll-speechtotext. Use this tool when you need to transcribe spoken language into text without uploading data to the cloud, and require features like speaker diarization for identifying individual speakers. It accepts audio inputs and produces text outputs, making it suitable for applications where local data processing is essential. Ideal for use cases where data privacy and security are a top priority, such as in research, interviews, or meetings.

Canonical page: https://skillsregistry.net/skills/sssamuelll-speechtotext  
JSON: https://api.skillsregistry.net/v1/skills/sssamuelll-speechtotext

## Description

Python library, CLI and MCP server for local transcription and speaker diarization. Nothing is uploaded.

## Trust

- **Trust score (0–1):** 0.56
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/sssamuelll/speechtotext)

## 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": "sssamuelll-speechtotext"
    }
  }
}
```

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