What it does
The resource converts audio and video into text and adds speaker diarization, which labels who is speaking, along with timestamps, a summary, action items and subtitles. The publisher describes it as oriented toward Russian-language content.
The listed features point to recordings where text is needed with speakers separated or with subtitles generated. The source does not describe setup, supported file formats or how the MCP server is run.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
Vibe2Text — AI audio & video transcription with speaker diarization
Audio & video to text, Russian-first: diarization, timestamps, summary, action items, subtitles.
v1.0.1As shown on registry.modelcontextprotocol.io when we last read it