Generate video with synchronized audio from a text prompt using Wan 3.0. Pick resolution, aspect ratio, and duration. Pay per generation, no subscription.
Wan 3.0 Text to Video generates a video with synchronized audio directly from a text prompt, with selectable resolution, aspect ratio, and duration.
About this model
Wan 3.0 Text to Video turns a written scene description into a video with synchronized audio in one asynchronous Muapi call. Choose 480p, 720p, or 1080p output, five aspect ratios (16:9, 9:16, 1:1, 4:3, 3:4), and a duration from 2 to 30 seconds. An optional thinking-mode flag gives the model more time to reason through complex, multi-subject prompts before generating, and audio can be toggled off if you only need a silent clip. For animating an existing image instead of writing a scene from scratch, see Wan 3.0 Image to Video; for guiding a shot with reference images, video, and audio together, see Wan 3.0 Reference to Video. For the higher-fidelity Prime tier, see Wan 3.0 Prime Text to Video. For a bolder, higher-contrast take on the same request shape, see Wan 3.0 Spicy Text to Video.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | From $0.10 per generation (720p, 2s) up to $6.00 (1080p, 30s) | Pay-per-generation, priced by resolution and duration, no subscription required. |
| Fal.ai | Not available | Wan 3.0 is not listed on Fal.ai at this time. |
| Replicate | Not available | Wan 3.0 is not listed on Replicate at this time. |
Pay-per-generation, priced by resolution and duration, no subscription required.
Wan 3.0 is not listed on Fal.ai at this time.
Wan 3.0 is not listed on Replicate at this time.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Describe the video you want to create. | A cinematic aerial shot of mist moving through a mountain valley at sunrise. |
| Resolution | Enum (3 options) | Output video resolution. | 720p |
| Aspect Ratio | Enum (6 options) | Output video frame dimensions. | 16:9 |
| Duration | integer | Video length in seconds. | 5 |
| Thinking Mode | boolean | Enable deep-thinking mode for complex prompts. | false |
| Enable Audio | boolean | Include a generated audio track with the video. | true |
| Seed | integer | Random seed for reproducibility. Use -1 for a random seed. | -1 |
Describe the video you want to create.
A cinematic aerial shot of mist moving through a mountain valley at sunrise.Output video resolution.
720pOutput video frame dimensions.
16:9Video length in seconds.
5Enable deep-thinking mode for complex prompts.
falseInclude a generated audio track with the video.
trueRandom seed for reproducibility. Use -1 for a random seed.
-1Developer documentation
Write the prompt: Describe the scene, subject, camera movement, and mood you want in the prompt field.
Set the output shape: Choose resolution (480p, 720p, 1080p), aspect_ratio (16:9, 9:16, 1:1, 4:3, 3:4), and duration (2-30 seconds).
Tune generation: Enable thinking_mode for prompts with complex or multi-step scene descriptions, and set enable_audio to false if you want a silent video.
Submit and poll: Send the request with your Muapi API key, store the returned request_id, then poll the prediction result endpoint or supply a webhook_url to receive the completed video URL.
curl -X POST https://api.muapi.ai/api/v1/wan3.0-text-to-video \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A cinematic aerial shot of mist moving through a mountain valley at sunrise.",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5
}'
Frequently asked
It generates a video with synchronized audio from a text prompt, with configurable resolution, aspect ratio, and duration.
480p, 720p, or 1080p resolution, five aspect ratios (16:9, 9:16, 1:1, 4:3, 3:4), and a duration of 2 to 30 seconds.
Yes, by default. Set `enable_audio` to `false` in the request to generate a silent video instead.
It enables a deep-thinking pass over complex, multi-subject, or multi-step prompts before generation starts, which can improve prompt adherence at the cost of extra processing time.
Pricing scales with resolution and duration, and the completed task response includes the exact charge for that generation.
Poll the prediction result endpoint with the returned `request_id`, or pass a `webhook_url` to be notified when the video is ready.