Skip to content
Fylane
Get API key

Free tools · Audio and video

Transcribe audio

Plain text, or SRT and VTT with timestamps. Runs on your credits in the console.

This one runs on your credits. Plain text, or SRT and VTT with timestamps. Runs on your credits in the console.

Sign in and get 500 free credits every month — enough for many files — then drop the file in the workbench and run transcribe audio there.

Pick a file below to see exactly what it would cost.

Sign in and run it — free credits included (opens in a new tab)

Runs on your credits in the console — 500 free a month, about 4 per megabyte here.

How to transcribe audio

  1. Sign in — 500 free credits a month.
  2. Drop the recording, choose text or subtitles.
  3. Run Transcribe and download.

What happens to your file

Speech is recognised by a model running inside Fylane’s own sandbox — the audio never leaves it for an outside service. Punctuation and paragraphing are inferred; speaker names are not.

SRT and VTT carry timestamps per phrase, ready for a video player or an editor.

Questions

Which languages?

English best; major European languages well; the model detects the language itself.

What does it cost?

Four credits per megabyte of audio. An hour of MP3 speech is around 40–60 MB, so 160–240 credits.

Do this in code

curl -X POST https://api.fylane.dev/v1/jobs \
  -H "Authorization: Bearer $FYLANE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "file_id": "<file id>",
    "operation": "audio.transcribe",
    "options": {
      "format": "text"
    }
  }'

The same operation, audio.transcribe — Speech to text: plain text, or timed SRT/VTT — transcribed in the sandbox, no third party. Upload first with the quickstart; every option is on the operations page. 500 free credits a month, then $5 per thousand.