# FFVoice

> Use this tool when you need to transcribe audio files or microphone input locally without cloud transmission, and require features like speaker diarization and real-time caption streaming. It solves problems such as inaccurate transcription, speaker identification, and slow captioning, and accepts audio files or microphone input with output as text transcripts. Ideal for use cases where privacy and real-time transcription are crucial, such as interviews, meetings, or lectures.

Canonical page: https://skillsregistry.net/skills/chicogong-ffvoice  
JSON: https://api.skillsregistry.net/v1/skills/chicogong-ffvoice

## Description

Transcribe local audio files and microphone input using on-device Whisper processing without cloud transmission. Provides speaker diarization to identify individual speakers, real-time caption streaming, and enumeration of available audio devices. Built with C++ and Python bindings for cross-platform audio capture.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/chicogong-ffvoice)
- **Repository:** <https://github.com/chicogong/ffvoice-engine>

## 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": "chicogong-ffvoice"
    }
  }
}
```

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