From a script
Paste a script, choose an AI voice and get a picture for every scene.
Upload a recording as MP3, WAV or M4A. Animatic transcribes it, times scenes to your voice and makes a picture for each one. Uploading uses no credits, and Ultra takes recordings up to 3 hours long.
100:00This week: a shop on a quiet street that only repairs one thing.Ready
200:41She seals the last crack with a thin line of gold.Ready
301:15Then she carries it up to the roof and lets it go.ReadyYour voice sets the pace, and every scene stays editable.
Add an MP3, WAV or M4A file. Animatic detects the language and transcribes it.
The transcript is split into scenes where the subject changes, each with a picture timed to your voice.
Remake any scene or change its timing, then export in 16:9, 9:16 or 1:1.
It works best when a voice tells a story or explains something: podcasts, lectures and recorded narration. If you want the hosts on screen, film them; Animatic illustrates what they're saying.
| Plan | Longest project |
|---|---|
| Free | 10 minutes |
| Creator | 1 hour |
| Pro | 2 hours |
| Ultra | 3 hours |
MP3, WAV or M4A. Upload the finished voiceover or the episode audio, and Animatic transcribes it from there.
No. Uploading uses no credits. The pictures do, starting at 3 credits per scene, and Studio shows the total before any are made.
Up to your plan's project length: 10 minutes on Free, 1 hour on Creator, 2 hours on Pro and 3 hours on Ultra.
You can upload its audio. Animatic makes pictures for what's being said. It doesn't use your camera footage or show the hosts on screen.
Animatic detects the language and transcribes it automatically. On paid plans, subtitles also render non-Latin scripts: Japanese, Chinese, Korean, Arabic, Cyrillic and Devanagari.
Start free with 100 credits and no card. Upgrade when you want longer recordings and exports without a watermark.