跳到正文
MCP ThesaurusMCP Thesaurus

vocce transcribe

社区Incomplete39/100认领

npm vocce-transcribe-mcpstdioupdated 1mo ago

Hosted audio/video transcription for AI agents and automations. No API key. No local model. Upload a file, get back text + SRT + VTT + timestamped segments — powered by Whisper large-v3 on vocce's GPU.

源码官网

vocce transcribe 能做什么?

vocce — agent integrations

Hosted audio/video transcription for AI agents and automations. No API key. No local model. Upload a file, get back text + SRT + VTT + timestamped segments — powered by Whisper large-v3 on vocce's GPU.

→ Product: https://vocce.io · API docs: https://vocce.io/api · OpenAPI: https://vocce.io/openapi.json

Three ways to use it

1. MCP server — for Claude, Cursor, Windsurf, …

{ "mcpServers": { "vocce": { "command": "npx", "args": ["-y", "vocce-transcribe-mcp"] } } }

Details → transcribe-mcp-server/

2. CLI — Python, stdlib only

python3 transcribe-cli/transcribe.py meeting.mp3 --format srt

Details → transcribe-cli/

3. Agent Skill — drop-in for Claude

See → agent-transcription-skill/

Also in here

How it works

Every package is a thin client: it uploads your file to vocce's hosted backend, polls until the job is done, and returns the result. The transcription runs on vocce's GPU — nothing to install, no model to download. The backend is the product; these clients are open source (MIT).

License

MIT