From words to motion
Describe the subject, action, camera and atmosphere in natural language.
Native Speech & SoundImage & Video ReferencesUp to 4K
Gemini Omni 1.1 Flash is Google's earlier Omni video model for 4 to 10 second clips with generated speech and sound. Use text, frames, or up to 7 images plus a reference video; for longer clips and video editing, choose Gemini Omni 1.2 Flash.
Start with the input that fits your idea. Available controls follow the selected model.
Describe the subject, action, camera and atmosphere in natural language.
Upload a starting image and describe how you want the scene to move.
Set both endpoints and describe the transition between them.
Reference images: up to 7. Reference videos: up to 1, 100 MB each and 10s total. Reference quota: 7 units total. An image uses 1 unit and a video uses 2 units; at most 1 video.
Durations: 4 / 6 / 8 / 10s. Resolutions: 720P / 1080P / 4K. Aspect ratios: 16:9 / 9:16.
720P · 1080P · 4KAudio is included automatically. This model does not offer an audio toggle here.
Choose one of the available modes: Text only / First frame (one image) / First & last frames / Multimodal references. Add the required visual inputs before generating.
Describe the action, camera movement, lighting and sound. Select your output settings and review the credit quote.
Generate your video, follow its status here, then preview and download. Use the result to plan another generation.
Generate AI images and videos with subscription credits or credit packs. They share one credit balance; image costs vary by model and resolution, while video costs vary by model and duration. New users get 10 free trial credits.
Cancel anytime
For individuals & casual creators
Ideal for personal projects & starters
For professional creators & teams
Most popular choice for professional creators
Designed for studios & enterprise scale
Enterprise solution for highest productivity
Available modes: Text only / First frame (one image) / First & last frames / Multimodal references. Frame images: JPEG, PNG or WebP, up to 20 MB each. Reference images: up to 7. Reference videos: up to 1, 100 MB each and 10s total. Reference quota: 7 units total. An image uses 1 unit and a video uses 2 units; at most 1 video.
Durations: 4 / 6 / 8 / 10s. Resolutions: 720P / 1080P / 4K. Aspect ratios: 16:9 / 9:16. With a video reference, the model chooses the actual output duration; the duration selector does not fix the final clip length. Audio is included automatically. This model does not offer an audio toggle here.
Review the live quote before generating. Model, duration, resolution, audio and reference video duration can affect the total. Your existing account balance is used.
Results appear below the generator. They also appear in Recent Creations in the video studio and in My Creations under the same account.
Yes. The model selector only lists available models in the same family. Switching opens that model’s page and keeps compatible draft inputs.
Audio is included automatically. This model does not offer an audio toggle here.