Validate
Extension, MIME, container signature, account access, size, and Credit ceiling are checked before the job starts.
Video to Markdown · Signed-in Beta
Upload a webinar, interview, product demo, class, or recorded call. Markovo extracts speech from the audio track and returns a time-coded transcript.
MP4, MOV, M4V, WebM, MKV, AVI, and WMV are supported up to 50 MB and 60 minutes. This Beta does not analyze video frames, slides, on-screen text, or speaker identity.
Verified output links appear here after conversion.
The output contains detected language, duration, model, time-coded speech segments, actual Credits, and bundle evidence. A file without a decodable audio track or recognizable speech fails without settlement.
Extension, MIME, container signature, account access, size, and Credit ceiling are checked before the job starts.
The bundled local model transcribes the video's audio track and records stable segment timestamps.
Use output.md directly or download the complete bundle with metadata, source map, quality report, manifest, and ZIP.
video-to-markdownBrowser, API, CLI, and MCP use the same account, Credits, History, and bundle flow.
Speech available in the selected container's decodable audio track becomes time-coded text.
Slides, captions burned into frames, diagrams, cuts, faces, and speaker diarization are not interpreted.
Estimate confirmation uses a conservative ceiling; settlement is 1 Credit per started minute and never exceeds that ceiling.
curl -X POST https://markovo.net/v1/convert \
-H "Authorization: Bearer ${MARKOVO_API_KEY}" \
-F "file=@webinar.mp4" \
-F "capability_id=video-to-markdown" \
-F "max_credits=60"markovo convert webinar.mp4 \
--out runs/webinar \
--max-credits 60markovo_convert({
"input_path": "webinar.mp4",
"max_credits": 60
})