Wan 3.0 Spicy Text to Video
Generate high-motion video with synchronized audio from a text prompt, with selectable resolution, aspect ratio, and duration.
Wan Spicy is the high-intensity sibling of Alibaba's Wan video family on Muapi, tuned for bolder contrast and more dramatic motion.The catalog covers Wan 3.0 Spicy text-to-video, image-to-video, and reference-to-video, Wan 2.7 and 2.6 Spicy image-to-video, and Wan 2.2 Spicy image-to-video and video extension through one asynchronous REST API.
Generate high-motion video with synchronized audio from a text prompt, with selectable resolution, aspect ratio, and duration.
Animate a source image with bold motion and synchronized audio, with optional end-frame guidance and resolution control.
Generate high-motion video from a prompt plus up to 10 reference images, 5 videos, and 5 audio references.
Animate a still image into bold, high-contrast motion with optional audio guidance, single- or multi-shot framing, and prompt expansion.
Create a dramatic image-to-video clip with optional audio-guided generation, shot control, and automatic prompt expansion.
The original Spicy image-to-video endpoint for fast, dynamic motion effects from one source image.
Continue an existing video with new frames that match its style while adding stronger, bolder motion.
Wan Spicy is Muapi's high-intensity tier of Alibaba's Wan video models. It uses the same underlying family while emphasizing bolder contrast, stronger motion, and more dramatic visual energy.
Four generations are available today: Wan 3.0 Spicy for text, image, and reference-to-video; Wan 2.7 Spicy and Wan 2.6 Spicy for image-to-video; and Wan 2.2 Spicy for image-to-video and video extension.
Turn a written scene into high-contrast, high-motion video with synchronized audio on Wan 3.0 Spicy.
Use an image, prompt, and optional audio guidance to shape pacing and motion on Wan 2.7 or 2.6 Spicy.
Guide Wan 3.0 Spicy with up to 10 images, 5 videos, and 5 audio references for consistent scenes.
Choose single-shot or multi-shot composition on the newer Wan 2.7 and 2.6 Spicy image workflows.
Continue an existing clip with the fast Wan 2.2 Spicy video-extend endpoint.
Share Muapi authentication, billing, request IDs, and result polling across every Spicy generation.
Create energetic clips with aggressive camera movement and synchronized sound for launch campaigns.
Generate bold, high-contrast short-form video that stays visually legible in fast feeds.
Use a guide track or Wan 3.0's native audio generation to coordinate movement and sound.
Keep characters, locations, and visual direction aligned with image, video, and audio references.
Extend an existing shot when a scene needs more time without changing its visual language.
| Model | Modes | Max resolution | Starting price |
|---|---|---|---|
| Wan 2.7 Spicy | Image to Video | 1080p | $1.00 |
| Wan 2.6 Spicy | Image to Video | 1080p | $1.00 |
| Wan 2.2 Spicy | Image to Video, Video Extend | 720p | $0.20 |
| Wan 3.0 Spicy | Text, Image, Reference to Video | 1080p | $0.055 |
Submit JSON with an x-api-key header, receive a request ID immediately, and poll the standard prediction result endpoint for the completed media URL.
curl -X POST https://api.muapi.ai/api/v1/wan3.0-spicy-text-to-video \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"A breakneck motorcycle chase through a neon city at night","resolution":"1080p","duration":5,"enable_audio":true}'
# Response: {"request_id":"REQUEST_ID"}Call the endpoint that matches your workflow, such as wan3.0-spicy-text-to-video or wan2.7-image-to-video-spicy.
curl https://api.muapi.ai/api/v1/predictions/REQUEST_ID/result \ -H "x-api-key: YOUR_API_KEY" # Use the matching wan2.7, wan2.6, or wan2.2-spicy endpoint for older variants.
Poll until the task completes, then read the video and synchronized audio output from the response.
Spicy is Muapi's name for the high-intensity sibling of a standard Wan endpoint: the same family tuned for bolder contrast, stronger motion, and more dramatic scenes.
Wan 3.0, Wan 2.7, Wan 2.6, and Wan 2.2 all have live Spicy endpoints. Wan 3.0 covers text-to-video, image-to-video, and reference-to-video; 2.7 and 2.6 cover image-to-video; 2.2 covers image-to-video and video extension.
Wan 3.0 Spicy generates synchronized audio by default and accepts enable_audio: false to disable it. Wan 2.7 and 2.6 Spicy accept an optional audio URL to guide pacing and motion.
Single-shot keeps one continuous composition. Multi-shot lets Wan 2.7 or 2.6 Spicy plan several connected shots from the same prompt and source image.
Create a Muapi API key, send it in the x-api-key header, call the endpoint for your chosen generation, and poll the returned request ID. No separate waitlist is required.
Get one Muapi API key and call every Spicy generation from the same asynchronous integration.