Audio to Markdown · Signed-in Beta

Turn recordings into time-coded Markdown.

Upload a meeting, interview, lecture, voice note, or podcast clip. Markovo keeps timestamps beside the words and reports transcription quality boundaries.

MP3, WAV, M4A, AAC, FLAC, OGG, OPUS, and WMA are supported up to 50 MB and 60 minutes. Credit v2 follows actual decoded audio milliseconds at 1 Credit per minute with a 0.3 Credit minimum.

Signed-in Beta · Cost shown first · Failed jobs spend nothing

Choose one audio file to get started.

Readable transcript, traceable timing.

The bundle records detected language, duration, time-coded segments, quality evidence, and the actual Credits settled. Timing is checked against the decoded source.

01

Validate

Markovo checks extension, MIME, media signature, account access, file size, and the confirmed Credit ceiling.

02

Transcribe

Speech becomes ordered segments with stable timestamps. Temporary processing failures fail safely and release reserved Credits.

03

Review

Download output.md or the full bundle with metadata, source map, quality report, manifest, and ZIP.

A transcription Beta with explicit boundaries.

Capability

audio-to-markdown

Browser, API, CLI, and MCP share one account, Credits balance, History, and bundle.

Best input

Clear speech

Low noise, audible voices, and a consistent recording level produce the safest result.

Billing

Actual decoded audio milliseconds

Credit v2 bills 1 Credit per decoded audio minute with a 0.3 Credit minimum and never exceeds the confirmed ceiling. Failed jobs cost 0.

Review and privacy

Names, overlap, and bounded processing

Proper nouns, accents, music, crosstalk, and speaker diarization can need review. Audio may be processed by Cloudflare Workers AI under the standard retention and deletion policy.

Use the same transcript capability 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=@meeting.mp3" \
  -F "capability_id=audio-to-markdown" \
  -F "max_credits=60"
CLI

Download the bundle

markovo convert meeting.mp3 \
  --out runs/meeting \
  --max-credits 60
MCP

Bound agent work

markovo_convert({
  "input_path": "meeting.mp3",
  "max_credits": 60
})