Talking characters
Dialogue with clear lip-sync and distinct multiple speakers, plus music and sound effects in the same clip.
Generate 15-second clips with synchronized speech, music and sound effects — or edit your own footage — with reference images that keep faces and brand colors consistent.
Google’s November 2026 update — 15-second clips, multi-turn conversational editing and closer reference following.
Draft, refine and upscale — with sound baked in.
Dialogue with clear lip-sync and distinct multiple speakers, plus music and sound effects in the same clip.
Refine the same clip turn by turn — swap products or backgrounds, change lighting, weather or camera angle.
Faces, garments, packaging typography and brand colors stay consistent across shots and camera angles.
Iterate cheaply at 360p or 720p, then render the chosen take at 1080p or 4K.
Interpolate between two frames with less visual drift, or extend a clip beyond its original end.
Build four-shot explainers from a single style frame — orbits and flythroughs with fewer unwanted jump cuts.
Pick a mode, configure the output and generate.
Text, up to 6 reference images, first & last frame, or edit an uploaded clip.
Describe the scene and any dialogue — or the edit, naming what must stay unchanged.
Aspect ratio, resolution and duration (3–15s; the clip length in Video Edit).
The studio estimates your cost live. Preview the video with sound and download it.
Answers to common questions about modes, audio and pricing.
Gemini Omni 1.2 Flash is Google’s video model that generates and edits clips with synchronized speech, music and sound effects from text, images and video — up to 15 seconds, from 360p drafts to 4K upscales.
Text to Video generates from a prompt. Reference Images (up to 6) keep faces, packaging and brand colors consistent across shots. First & Last Frame interpolates between your two frames (3–10s). Video Edit refines an uploaded clip of up to 15 seconds — swap a product, change the weather, restyle the scene.
3 to 15 seconds in one-second steps. With both a first and last frame the range is 3–10 seconds. Video Edit keeps the length of the input clip and is billed on that length.
Yes — every clip can carry native synchronized speech, music and sound effects, with clearer lip-sync and distinct multiple speakers. Audio is generated automatically; it is not an input.
360p, 720p (the default), 1080p and 4K. Google recommends drafting at 360p or 720p, then upscaling the chosen take to 1080p or 4K. Aspect ratios: 16:9, 9:16 or auto.
Per second of output by resolution: 10 gems/s at 360p, 20 at 720p, 40 at 1080p and 80 at 4K. Video Edit is billed on the input clip’s length. A 5-second 720p clip costs 100 gems.
Refine the same clip turn by turn instead of starting over — swap a product or background, change lighting, weather, camera angle or aspect ratio, while references keep faces and brand colors consistent.
Start with a prompt, references or your own footage and generate videos with native audio.
Start creating with Gemini Omni