Upload any video or audio file. Lumo extracts the audio and transcribes it with word-level precision. No manual syncing, no fuss.

Choose from 11+ fonts, pick custom colours, and set your animation mode. Pop-on, karaoke highlight, or word-by-word reveal. Fine-tune timing and position until every frame feels right.

Render frame-by-frame at up to 4K resolution. Lumo bakes the styled captions directly into your video and hands you a ready-to-post MP4.