Offline speech-to-text & speaker diarization MCP server: transcribe audio on-device, no cloud
Offline speech-to-text & speaker diarization MCP server: transcribe audio on-device, no cloud. That is what the ffvoice mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.
If raw ASR accuracy or throughput is your primary concern, evaluate whisper.cpp directly or consider specialized runtimes. ffvoice's value is the integrated pipeline, not the ASR engine itself.
The server publishes 5 tools. What each one is for:
transcribe_file — 转写本地音频文件（WAV/FLAC 等），支持语言选择、模型大小、词级时间戳transcribe_file_with_diarization — 转写并标注说话人 —— 每段带 speaker_id，回答"谁在何时说什么"（需 pip install 'ffvoice[diarization]',免编译）capture_and_transcribe — 录制指定时长的麦克风音频并实时转写（内置 VAD 分段 + 可选 RNNoise 降噪）capture_and_caption — 录制麦克风音频并产出实时字幕流（LiveCaptioner，partial/final 事件）list_audio_devices — 列出所有可用的音频输入/输出设备及默认设备 IDInstallation goes through your MCP client rather than a global install: point it at ffvoice on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Ffvoice's toolset — transcribe_file, transcribe_file_with_diarization, capture_and_transcribe and 2 more — is a fair guide to whether it matches your workflow. It is maintained by chicogong; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| transcribe_file | 转写本地音频文件（WAV/FLAC 等），支持语言选择、模型大小、词级时间戳 |
| transcribe_file_with_diarization | 转写并标注说话人 —— 每段带 speaker_id，回答"谁在何时说什么"（需 pip install 'ffvoice[diarization]',免编译） |
| capture_and_transcribe | 录制指定时长的麦克风音频并实时转写（内置 VAD 分段 + 可选 RNNoise 降噪） |
| capture_and_caption | 录制麦克风音频并产出实时字幕流（LiveCaptioner，partial/final 事件） |
| list_audio_devices | 列出所有可用的音频输入/输出设备及默认设备 ID |
{
"mcpServers": {
"ffvoice": {
"command": "uvx",
"args": ["ffvoice"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.