# ffvoice-engine

> ffvoice-engine — chicogong-ffvoice-engine. Use this tool when you need to perform offline speech-to-text and speaker diarization tasks, enabling AI agents to transcribe audio and identify individual speakers without relying on cloud services. It takes in audio files or streams as input and outputs transcribed text and speaker labels. Ideal for applications requiring on-device, real-time speech recognition and diarization, such as voice assistants, meeting transcription, and audio analysis.

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

## Description

Offline speech-to-text & speaker diarization for AI agents — Whisper ASR + MCP server + CLI + Python bindings, fully on-device, no cloud | 离线语音识别与说话人分离,Agent 开箱即用

## 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:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](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-engine"
    }
  }
}
```

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