What is VoxelStudios?

VoxelStudios is a generative video editor. Create shots with text-to-video, image-to-video, voice acting, and clip extension, then assemble them on the timeline and export up to 4K. Available models include Seedance 2.5, Seedance 2.0, Veo 3.1 Fast, Kling 3.0 Omni, HappyHorse 1.0, GPT Image 2, Seedream 5 Lite, and more. The Agent is coming soon.

How does generative video creation work?

Pick a generation model for a shot, enter a prompt, add any supported references, and create the result using the credit cost shown in the editor. Video models include Seedance 2.5, Seedance 2.0, Veo 3.1 Fast, Kling 3.0 Omni, Kling Motion, and HappyHorse 1.0. Image models include GPT Image 2, Seedream 5 Lite, Nano Banana Pro, and FLUX.2 Klein. The Agent is coming soon.

What is character consistency in generative video editing?

Drop a reference image and tag it as "character" in the multi-reference panel. Every subsequent generation receives that same reference and role tag, so the person or look carries from shot to shot. You can layer additional references for style, scene, object, or composition and switch image models without losing them. The references work across Nano Banana Pro, Seedream, and GPT Image 2.

Is VoxelStudios free to use?

Yes. Free accounts include the browser editor, project snapshots, and editor exports up to 4K. Annual Pro is $29 per month and adds Unlimited Generations plus 2,400 monthly credits for premium models and higher quality settings. Month-to-month Pro is $49 per month with the same premium credit allowance, but does not include Unlimited. Pro unlocks all current generation models, references, and multi-camera authoring. Enterprise adds timeline comments and review collaboration, commercially cleared generation models, REST API access, signed webhooks, custom terms, 4K video upscaling when generated footage needs it, and custom storage. Existing comments and multi-camera edits remain viewable after a downgrade, but editing requires the applicable plan. Paid users can purchase one-time credit packs when they need more.

What generative models are available in VoxelStudios?

Image: GPT Image 2, Seedream 5 Lite, Nano Banana Pro, and FLUX.2 Klein. Video: Seedance 2.5 (multimodal, 4 to 30 seconds), Seedance 2.0, Veo 3.1 Fast, Kling 3.0 Omni, Kling Motion, and HappyHorse 1.0. Processing tools include image upscaling and Pro or Enterprise access to 4K video upscaling when generated footage needs it. The Agent is coming soon.

Can I use VoxelStudios in my browser?

Yes, VoxelStudios is a fully web-based application that runs in your browser. No download or installation is required. It works on modern browsers including Chrome, Firefox, Safari, and Edge. The editor uses WebGL for high-performance video preview rendering and supports 4K export quality directly from your browser.

How do I extend a video clip?

Select the clip in your timeline and use Generative Clip Extension. The model analyzes your existing footage and generates additional frames that seamlessly continue the action. This is useful when you run out of footage or want to hold a shot longer without obvious looping. The generated extension maintains the style, motion, and content of your original clip.

What export formats does VoxelStudios support?

VoxelStudios supports MP4, WebM, MOV, and GIF exports on every plan. You can export in resolutions up to 4K with customizable frame rates, including 24, 30, and 60 fps. Generation credits are charged when you create generative media, not when you edit or export a project.

Capabilities

Built for
the cut.

AgentComing soon

Describe your idea. The agent writes scripts, picks models, generates shots, and assembles a cut you can edit.

Latest Image Models

Choose the right model for each shot from Nano Banana Pro, Seedream 5 Lite, Seedream 4.5, and GPT Image 2. Add role-tagged references for greater control.

Latest Video Models

Create from text, images, references, or motion controls with Seedance 2.5, Seedance 2.0, Veo 3.1 Fast, Kling 3.0 Omni, and HappyHorse 1.0.

Character Consistency

Tag any reference image as a character, style, scene, or composition. The same look carries across every shot.

Clip Extension

Extend any clip beyond its original length with generated frames that match your footage.

Voice & Audio

ElevenLabs voice acting with lip-synced delivery, plus music and SFX generation directly on the timeline.

Toolkit

AgentComing soonCharacter ConsistencyMulti-reference TaggingText-to-VideoImage-to-VideoVoice Acting (lip-sync)Clip ExtensionVideo UpscalingAuto-CaptionsColor GradingMulti-model Generation

Final cut

Ready when
you are.

Join thousands of creators using generative tools to produce stunning videos.

Built forthe cut.