Validate
Extension, MIME, container signature, account access, size, and Credit ceiling are checked before the job starts.
Conversion details & limits
Video to Markdown Converter from the Audio Track.
Upload a webinar, interview, product demo, class, or recorded call. This video transcript to Markdown workflow extracts speech from the audio track and returns time-coded text. Download the result as Markdown (.md).
MP4, MOV, M4V, WebM, MKV, AVI, and WMV are supported up to 50 MB and 60 minutes. Credit v2 follows actual decoded audio milliseconds at 4 Credits per minute with a 0.3 Credit minimum. This Beta does not analyze video frames, slides, on-screen text, or speaker identity.
Your videos.
Ready to work.
Bring the spoken track into your notes.
Delivery ready
Your Markdown is ready
Verified output links appear here after conversion.
Optional: download audit files for verification or troubleshooting.
Delivery ready
Your link, in Markdown
01 / How it works
Transcribe what was said, without guessing what was shown.
The output contains detected language, duration, time-coded speech segments, actual Credits, and bundle evidence. A file without a decodable audio track or recognizable speech fails without settlement.
Listen
Speech in the video's audio track becomes ordered, time-coded text. Temporary processing failures release reserved Credits.
Review
Use output.md directly or download the complete bundle with metadata, source map, quality report, manifest, and ZIP.
02 / What you get
Audio transcription is included; visual analysis is not.
video-to-markdown
Browser, API, CLI, and MCP use the same account, Credits, History, and bundle flow.
Spoken content
Speech available in the selected container's decodable audio track becomes time-coded text.
Frames and speakers
Slides, captions burned into frames, diagrams, cuts, faces, and speaker diarization are not interpreted.
Actual decoded audio milliseconds
Credit v2 follows actual decoded audio milliseconds at 4 Credits per minute with a 0.3 Credit minimum and never exceeds the confirmed ceiling. Failed jobs cost 0.
03 / Source details
Use the same audio-track transcript from code or an agent.
API
Confirm a 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"CLI
Download the bundle
markovo convert webinar.mp4 \
--out runs/webinar \
--max-credits 60MCP
Bound agent work
markovo_convert({
"input_path": "webinar.mp4",
"max_credits": 60
})04 / Connect your tools
Review output from the Video to Markdown Converter.
This route transcribes the decodable audio track. It does not analyze frames, slides, faces, diagrams, burned-in captions, scene changes, or other visual evidence.
Confirm the container has useful sound
Speech must be present in a supported audio track. Silent files or media without recognizable speech can fail without settlement.
Use time-coded text for navigation
Segments help you return to the recording, but they do not identify speakers or describe what appeared on screen.
Keep the video for visual context
Review names, numbers, and technical terms against the audio, and consult the original video whenever the meaning depends on a demonstration, slide, chart, or caption.
Video to MD questions
What is a Video to MD converter?
Video to MD transcribes the audio track of an uploaded video into Markdown (.md). It does not describe video frames or silently summarize the speech.