Turn your video into polished, word-synced captions directly in your browser. Transcribe, edit every word, style the look, preview it live, and burn it into your export.
Whisper client-side AI
Word-level timing
WebGPU + WASM
MP4/WebM recording
Make it pop. Make it yours.
01 / 00:18.42word-perfect preview
01 — Create captions
Your video stays in this browser tab.
Local AI
↑
Drop your video hereMP4, MOV, WebM and common browser formats
For best performance, use a short-form clip under 5 minutes.
Choose a video to begin.0%
Use my own transcript / SRT
Paste plain text or SRT. SRT timings are preserved; plain text is aligned against detected speech regions.
02 — Word editor
Click a word to seek. Edit text or timing.
Live preview
Your final caption layer, frame by frame.
00:00
Caption timeline00:00
03 — Export
Real-time canvas + audio recording.
The browser renders the video and caption layer together. Export speed is real-time, so a 60-second clip takes about 60 seconds.