# Launch Day!

Convo Mode (Editable NotebookLM Audio) is now live!

[Test it out](/content/archive/tools-archive/ai-podcast-generator/index.html)

## Create using the best models

[Start creating](/content/studio/index.html)

# Text to Video AI models, built for real work

Generate videos from text prompts using best-in-class AI models, then structure, refine, and ship usable video through workflows, Wonda, and a real editor.

What are text to video AI models?

Text to video AI models generate video directly from your prompts. They can create scenes, motion, camera movement, and visual storytelling without starting from footage. But raw generation is only the first step.

Wondercraft integrates text to video models as part of a larger system, so teams can turn generated clips into structured, branded, and usable video for real business needs.

# How text to video works in Wondercraft

### Step 01

**Describe the video**

Start with a text prompt describing what you want to create: a training clip, explainer, announcement, or first draft.

### Step 02

**Generate with the right model**

We select and run the best text to video model for the job, optimised for realism, motion, or style.

### Step 03

**Let Wonda work**

Wonda helps regenerate, iterate, and adjust the result, improving structure, pacing, or tone without manual editing.

### Step 04

**Finish in the Studio**

Edit the video on a real timeline: adjust timing, add captions, music, branding, and export ready-to-use versions.

# Available text to video AI models

Wondercraft isn’t just “AI video.” It’s the platform that makes models like Sora 2 actually useful in real creative workflows:

- **Sora 2 Pro**: Start from a sentence or storyboard — Wondercraft turns it into a cinematic scene.
- **Sora 2**: High-quality text to video generation with strong realism and motion.
- **Google Veo 3.1**: Text to video model focused on cinematic visuals and prompt adherence.
- **Seedance 1.0 Pro**: Multi-shot video generation with strong scene continuity.
- **Kling 2.6**: Start from a sentence or storyboard — Wondercraft turns it into a cinematic scene.
- **Kling 2.5**: Stable text to video generation optimised for consistency.
- **Kling 01**: Earlier-generation Kling model supported for compatibility.
- **PixVerse V5**: Stylised text to video output with fast iteration.
- **WAN 2.5**: Efficient text to video generation for rapid drafts.

## Frequently asked questions

### What is a text to video AI model?

A text to video AI model generates video content directly from written prompts, creating scenes, motion, and visuals without starting from footage.

### Does Wondercraft use only one text to video model?

No. Wondercraft integrates multiple best-in-class text to video models so it can choose the best tool for different types of content.

### Do I need to choose a model myself?

Not usually. In most workflows, Wondercraft and Wonda handle model selection automatically. Advanced users can explore individual models if needed.

### Can I edit text-to-video output?

Yes. All text-to-video output can be edited in Wondercraft’s Studio with full timeline control.

### Is text to video suitable for business use?

Yes — when combined with structure, branding, and editing. Wondercraft is designed to make text to video usable inside real organisations.