Audio & video → WebVTT · SRT · TXT · MD

Sound in. Subtitles out.

Your first 2 minutes are free. The rest is $1.50. Drop in an MP3, podcast, lecture or video — AI writes the captions, you keep all 4 formats. No account, no subscription.

Drop a file here or browse

MP3, M4A, WAV, MP4, WebM, MOV · free 2-minute preview · max 500 MB

Sample output ✓ synced cues

00:00:01.24000:00:04.880 Welcome to the future of subtitles.

00:00:05.30000:00:08.610 Drop any file and watch it become text.

  • Free preview

    120s

  • Formats

    .vtt .srt .txt .md

  • Account

    Not required

  • Max upload

    500 MB

How it works

1 · Drop it in

No account, no forms, no waiting for a welcome email.

2 · Hear the preview

Your first 120s come back as captions — free. Listen and decide.

3 · Keep it all

$1.50 unlocks .vtt, .srt, .txt and .md. Yours forever, nothing recurs.

Frequently asked questions

Is there really a free preview?

Yes. Upload any file and you get the first 2 minutes transcribed and shown as a live WebVTT preview for free — no account, no card required. You only pay when you unlock the full project export.

How much does a full export cost?

A single full project export is $1.50, or 1 credit. Credit packs (3 and 10 exports) bring the per-export price down. There are no subscriptions — you pay as you go.

Do I need to create an account?

No. You can upload, preview and pay for a single export with zero registration. A free account is optional — it only adds a credit balance and download history for repeat use.

What formats do I get?

Every unlock downloads all four: .vtt (WebVTT), .srt (SubRip), .txt (plain text) and .md (Markdown). WebVTT works natively in HTML5 <video> and YouTube; SRT is the interchange standard for editors and encoders.

Which files are supported?

Audio: MP3, M4A, WAV, OGG, FLAC, AAC. Video containers: MP4, WebM, MOV (the audio track is extracted automatically). Files up to 500MB are accepted; long files are split and merged for you.

How long can my audio be?

There is no hard cap on length. Whisper processes ~25 minutes per request, so longer files are automatically split at silence and joined back together with correct timing — a 1-hour podcast works fine.

What happens to my upload?

Files are processed on the server and then deleted after export — we do not keep your audio or share it. See the privacy note on the home page.

How accurate is the transcription?

We use OpenAI Whisper, one of the most accurate speech-to-text models, with automatic language detection and proper punctuation. For a full export you can review the sample first before paying.

Which languages are supported?

Whisper supports 99+ languages with automatic detection. Subtitles are timestamped to match your video so they display inline as you play.

Are the timecodes accurate?

Yes — every cue carries precise start/end millisecond timestamps (HH:MM:SS.mmm for VTT, HH:MM:SS,mmm for SRT), so captions stay in sync with your video or podcast.