New
You, on camera.
Kinema around you.
Record one take to camera, or generate one: lip-synced avatar video is built in, powered by HeyGen. Kinema uses your audio as the narration, keeps you on screen where it hits hardest, and carries everything else with sourced b-roll, graphics and score.
Upload or generate your take
One continuous clip of you talking to camera, or a lip-synced avatar take generated inside Kinema with built-in HeyGen. The audio becomes the voiceover for the film.
Kinema places you
The planner marks the beats where a face carries more than footage: openings, turns, punchlines. Those stay on camera.
B-roll carries the rest
Everything between your on-camera beats is covered with sourced footage, graphics and music, cut to your delivery.
STANDARD COVERAGE
Mostly b-roll
You appear at the moments that matter most. Roughly a quarter of the runtime is on camera.
- Best for documentary-style channels
- Strong hooks and chapter turns on camera
- B-roll everywhere else
HIGH COVERAGE
Mostly you
Over half the runtime stays on camera, with b-roll as punctuation instead of the default.
- Best for commentary and personality channels
- Cutaways only where footage tells it better
- Same sourcing, graphics and score