Paste your script. Each paragraph (or two sentences) becomes a scene, matched to an image by filename keywords, otherwise in upload order. Sound effects and timing are suggested automatically.
Premium voices use more of your Cloudflare allowance (about 8,000 characters for a 1,300-word script). Budget voices cost almost nothing.
Music fades in at the start and out at the end automatically.
Need timed captions from your voice? Make a free .srt with CapCut auto-captions, YouTube Studio or Whisper, then import it here.
Try the built-in sound effects (add them to scenes in the Scenes tab):
Film looks need Chrome or Edge. Shortcuts: Space = play/pause, ← → = skip 5s.
Exports 1920×1080, 16:9, 30 fps. Chrome and Edge render much faster than real time. Other browsers fall back to real-time rendering, which takes as long as the video. Keep this tab open.
A project file holds your images and audio, so you can move a project to another device or keep a backup.
Cloud render (long videos)
For 8–10 minute documentaries, or phones that struggle. Uses your own render server. Leave empty to render in this browser.
YouTube thumbnail
Uses the image of the selected scene (1280×720).