Animoso draws the motion graphics, records a natural voice, checks every line and puts word-by-word captions on it. All on your own computer.
This ad for a music school was made from ten short lines. Press play with the sound on.
Most tools give you a timeline and leave the rest to you. This one records, listens, times and lines everything up, then lets you change any part.
Each line is recorded more than once. The app listens back, makes sure every word was said clearly, and keeps the best take. Lines that still sound wrong are flagged for you.
Computer voices often fall flat at the end of a sentence. Excited lines and lines ending in "!" finish on a rising tone instead, so an ad sounds like it means it. You choose how much, line by line.
Every word is timed from the real recording, so captions and motion land exactly when it is said.
Kinetic titles, glowing intros, feature cards, 1-2-3 steps, counting numbers, phone screens with taps, photo moves and end cards. Sharp at any size, no stock footage needed.
Link the AI you already pay for, and ask it for a script or a change in plain words.
Click something in the live picture and it opens. Edit words, move a layer, trim the music, drag a sound effect. Most changes show at once.
When you finish a video, tell it what you liked and what you didn't. Those notes are kept and read before your next video.
The voices run on your computer: no upload, no per-minute charge. The music and sound effects are made by the app too, so there is nothing to license.
When a new version is out, the app tells you and downloads only the parts that changed, often about 1 MB instead of the whole app. One click restarts it on the new version.
Sign in once and the app works offline for up to 7 days, on a plane or a bad connection. It checks in by itself the next time you are online.
Show an app or website in a phone or screen frame, with taps and boxes on the right word.
Clear steps, a calm voice and captions, so learners can follow with the sound off.
Bold titles, an excited voice with rising endings, and an end card with your button.
Tall, square, feed or wide: pick the shape and every scene lays itself out again.
Type the lines yourself, or ask your linked AI to write the script and pick the scenes. Add your photos, logo and colours.
The app records the voice, checks it, times the captions and draws the motion. Change anything in the live picture until it feels right.
Get an mp4 and a caption file (.srt), ready for YouTube, Facebook, TikTok or a class page.
Then buy a pass when you need one. Passes never renew by themselves, so you are never charged without asking.
After the trial the app keeps working; exported videos carry a small watermark until you buy a pass. Your AI is billed by your AI company, not by us.
No. You can type the lines and change the scenes yourself. An AI makes it faster: if you already use Claude Code, Codex CLI or Gemini CLI on your computer, the app can use it. Linking an AI with an API key (useful on phones later) is coming soon.
Nothing is deleted and the app keeps working. The only difference: videos you export carry a small watermark until you buy a pass.
Yes, for up to 7 days at a time. You need internet to sign in, to pay, for the one-time voice download, and for your AI if it runs online.
Every account includes 2 computers. You can add more seats, or remove an old computer to free its place (a few times a month).
Not yet. Windows is first. A Mac app and an Android app (downloaded from this website) are coming soon; one account will work on all of them. There are no plans for iPhone for now.
Yes, the videos you make are yours. The voices, music and sound effects come with the app. Photos, logos and clips you add must be ones you have the right to use.
On your own computer. We never receive your scripts, photos or videos. Backing up to your own Google Drive is coming soon.
Inside the app, through PayMongo: card, GCash, Maya, GrabPay or QR Ph. The app notices the payment by itself within a few seconds. More about paying