Your raw recording. Edited for you.
Attach a recording of you talking. Kinisma cuts the pauses, filler words and retakes, then adds animated graphics, illustrations and doodles timed to your words, captions in their own band, zooms and music.
One prompt. Here’s everything the agent does.
Attach a raw recording of you talking and say what it’s for. Kinisma keeps your voice, your words and your recording’s shape, cuts what you’d cut yourself, and adds graphics timed to what you say. You approve a storyboard before anything is drawn or built. A few minutes of recording costs well under $0.50 in AI, music included.
“A short YouTube explainer for website owners. Keep it tight and clear.”
- You attach your recordingYou
MP4, MOV, M4V, WebM, MKV or AVI, up to 1 GB, with clear speech. Say in a sentence what it’s for.
- Listens to the recording
Every word is transcribed with its timing. If one speech-to-text model is busy, another takes over.
- Plans the cut
Drops dead air, false starts, retakes (keeping the last clean take), stumbles and tangents, tightens the pauses and removes “um”s, keeping every sentence whole.
- Plans the graphics
A graphic about every 6–10 seconds, landing on the exact words: animated diagrams and charts, AI illustrations (optional) or hand-drawn doodles, full frame or beside you.
- You approve the storyboardYou
One panel per section, with what’s on screen. Nothing is drawn, generated or coded until you approve, or ask for changes in plain words.
- Makes the graphics and builds the edit
Draws the pictures and doodles, designs the animated graphics, reviews the edit, then cuts your recording with zooms and punch-ins on the jump cuts.
- Adds the music
Music under your voice: composed by AI, a free Creative Commons track with its credit, or none.
- You watch it and ask for changesYou
It plays in the app. “Keep the sentence about pricing” or “make it tighter”: only what’s needed is rebuilt.
- Export or publish to YouTubeYou
Export an MP4, or upload it to your YouTube channel straight from the Publish screen with its title, description and thumbnail.
What’s in every video edit video
Your words, your voice and your recording’s shape stay as they are.
Pauses, filler words, retakes and stumbles removed, with sentences kept whole.
Animated diagrams, charts and mock-ups that build as you speak.
AI illustrations if you want them, or stock photos and hand-drawn doodles.
They never cover the graphics. Section titles become chapter headings.
Zooms and punch-ins on jump cuts, and music under your voice.
What people make with it
Get a better first draft
Say a line again if you fluff it. Kinisma keeps the last clean take.
“A 3-minute tip for my SEO channel” sets the pace, the graphics and the captions.
“Change the graphic in section 3 to a bar chart” rebuilds just that part.
Other tools make you do the work. Kinisma does it for you.
Kinisma vs video editing tools
Descript and CapCut make cutting easier, and Submagic adds captions and zooms, but you still make and place the graphics. A freelance editor does it all, in days.