Free beta · No card, ever
Captions that look
designed, not defaulted.
Upload a video, get word-timed subtitles, style every caption your way, export an MP4. Built for creators who post daily.
Made for Reels · Shorts · TikTok
Idea to posted, start to finish
Upload
Drop in an MP4, WebM, or QuickTime clip up to 5 minutes. It stays on your device. Only the audio uploads when you press Transcribe.
Transcribe
Speech-to-text with word-level timing and auto language detection. Every second is metered against your monthly minutes, shown live in your account.
Transliterate
Romanized Hindi, Bengali, Tamil, Telugu and more. Same word timing, new script, fully offline.
Style
Per-caption control over type, color, outline, box, spacing, and motion: pop, karaoke, spotlight, trail and more. Save looks as presets, preview everything live.
Export
Render a true MP4 plus SRT and VTT sidecars. What you preview is what renders: same engine, same frame.
Everything within reach
Per-caption styling
Every caption carries its own look. Change one without touching the rest.
Motion presets
Pop, karaoke, spotlight, trail and more. Tuned per caption, previewed live.
True preview
The canvas renders with the same engine as export. No surprises.
Local-first privacy
Your video never leaves your device. Press Transcribe and only the audio goes for speech-to-text and is deleted right after.
Metered transcription
Monthly minutes tracked honestly in your account. No card, ever.
SRT + VTT export
Take the text tracks with you alongside the rendered video.
Common questions
01Is Capsly free?
Yes. The beta is completely free, no card required. You get 15 minutes of transcription per month and 10 uploads per day. Paid tiers arrive with the public launch.
02What videos can I use?
MP4, WebM, or QuickTime files up to 5 minutes and 500 MB, picked from your device, never uploaded. Short-form vertical or horizontal: the canvas adapts to your footage.
03Where does my video go?
Nowhere: your video never leaves your device. Press Transcribe and only the audio goes once for speech-to-text, then it's deleted. Captions and styling are saved locally; when you come back, re-picking the file reconnects the picture. Skipping transcription means zero uploads, period.
04Can I pick videos from Google Photos or cloud libraries?
Unreliably: cloud libraries sometimes hand the browser files that change or vanish mid-session, which fails loudly or not at all. Download the video to your device first; local files just work.
05How is transcription metered?
Each transcribe spends your monthly minutes based on the measured audio length, never our estimate or your claim. A live meter in the app shows exactly where you stand.
06What do I get on export?
A rendered MP4 with your styled captions burned in, plus SRT and VTT sidecar files. The preview uses the same render engine, so the export matches pixel for pixel.
07Which browser do I need?
Any modern browser for editing. Export renders locally via hardware H.264, so a recent desktop Chromium gives the best results.
Free beta · No card, ever
YOUR NEXT VIDEO DESERVES BETTER CAPTIONS.
Join the free beta. Upload your first video and export styled subtitles in minutes.
Start creating free