Start with the right input
Text-to-video and image-to-video create a new clip. Other workflows start from a portrait, first and last frames, reference images or source video.
- Text and image inputs
- Portrait and speech for avatars
- Reference frames and source video
9:16
9:16
9:16One studio, a workflow for each job
Each workflow decides which models and fields you see. This clip uses first and last frame: Kling 3.0 Pro turned two generated stills into one five-second shot. Motion transfer, lip sync, video editing and upscaling take other inputs.
- Text, image and first/last-frame clips
- Talking avatars and lip sync
- Motion transfer, editing and upscaling
16:9
Check before you generate
Choose the workflow and a compatible model, prepare the source material and see the current credit price before you confirm.
- Formats depend on the workflow
- Rights confirmation for faces and voices
- Every result is saved to Lab
What you can make
Everything you can make in Video Studio
Works well with
What pairs well with Video Studio
Director: the AI video director
When one clip grows into a whole story, let Director plan the script and every scene.Audio Studio: AI voice, music and sound effects
Give an avatar its voice: generate the speech first or bring an ElevenLabs track.DUB: AI video dubbing and translation
Translate the finished clip into another language in a voice that matches the speaker.
All VlogMe services
One VlogMe account · one credit balance · everything saves to Lab
Questions about Video Studio
Can I turn an image into a video?
Yes. Image-to-video uses your image as the input and creates a clip with the motion you describe.
Does every model work with every workflow?
No. Inputs, length and formats depend on the workflow and model you choose.
Where do I edit a finished video?
Use Video Editor to trim, crop, retime, grade, add text or upscale. Use Aisma to change what happens in an existing clip.
Can I make a news video?
Yes: News Videos: AI news video generator researches a topic in today’s news, drafts the script and makes a presenter-led video. You approve the script before anything is generated.
Choose the input. Get the clip.
Start from text, an image, two frames, a portrait or existing footage. Every clip is saved to Lab, ready to edit, upscale or publish.





