AI video generator inside Claude, ChatGPT and Codex
Makemancer is an AI video generator that works inside Claude, ChatGPT and Codex. Describe a shot or share a still, and the assistant sends it to Seedance, Kling, Wan, MiniMax or another video model, then returns the clip with sound. Video starts at $0.15, and every request is quoted before it runs.
- Bring
- A sentence, or an image to start from
- Get
- An MP4 clip of up to 30 seconds
- From
- 15 credits · $0.15
- Works in
- ClaudeChatGPTClaude CodeCodex
Made with it
Our own results, first takes. Each caption says what it took.
How to do it
Connect Makemancer
Add Makemancer to Claude, ChatGPT, Claude Code or Codex. The steps for each app are on the connection page.
Describe the shot, or share a still
Write one shot: subject, action, camera and sound. If you already have a picture, send it and say how it should move. Draft cheaply first.
Make a 5-second 16:9 video: a slow push-in on a desert motel at blue hour, the neon sign flickers on, a car passes on the highway. Use Seedance 2.0 Mini at 480p and tell me the cost first.Keep the take you like, then upgrade it
Change one thing at a time until the motion is right. Then render the same shot at a higher resolution or on a premium model.
Good. Keep the same shot and render the final at 720p. Quote it first.
Which model to use
| Model | Best for | Priced for | Credits |
|---|---|---|---|
| Seedance 2.0 Minivideo/seedance-2.0-mini | Low-cost drafts, 4-15 s at 480p or 720p with sound. | 480p · 5 s | 15$0.15 |
| Seedance 2.5video/seedance-2.5 | Premium cinematic clips, 4-30 s, rich references and first and last frames.Opens after your first credit purchase | 480p · 5 s | 93$0.93 |
| Kling 4.0video/kling-4.0-omni | Directed motion and native audio, 3-30 s at 720p or 1080p.Opens after your first credit purchase | 720p · 5 s | 157$1.57 |
| Wan 3.0video/wan-3.0 | Steady framing with native audio, 2-30 s from 480p to 1080p.Opens after your first credit purchase | 480p · 5 s | 33$0.33 |
| MiniMax H3video/minimax-h3 | Detailed 768p or 2K output, 4-15 s, with native audio. | 768p · 4 s | 64$0.64 |
| Gemini Omni 1.1 Flashvideo/gemini-omni-flash | The default video model: fast, with native audio. | 720p · 4 s | 40$0.40 |
Text or image: which to start from
- Text to video is fastest to try: one sentence becomes a clip. Use it when the exact framing does not matter yet. See text to video.
- Image to video gives the most control: make or upload a still you like, then animate it. The product, the face and the colours stay put. See image to video.
What the three clips above cost
The desert motel shot is the same still animated by Seedance 2.0 Mini at 480p. The paper boat came from a text prompt on Wan 3.0 at 480p. The pottery wheel came from MiniMax H3 at 768p. Each example page lists the full prompt and the credits it used.
Questions
What is the best AI video generator to use from Claude?
There is no single best one. Seedance 2.0 Mini is the cheapest way to draft, Gemini Omni Flash and MiniMax H3 are ready from your first request, and Seedance 2.5 and Kling 4.0 give the most cinematic takes once they open after your first credit purchase. With Makemancer you can try several in the same chat.
Can the AI video generator start from my own photo?
Yes. Share the image and describe the motion. The image becomes the first frame; some models also take a last frame.
Do the videos have sound?
Most models here generate audio with the picture, including Seedance, Kling, Wan, MiniMax H3 and Gemini Omni. Describe the sound you want in the prompt.
How much does an AI video cost?
From $0.15, depending on model, length and resolution. A 5-second 480p Seedance 2.0 Mini clip costs $0.15. Failed jobs return their credits.