VideoWan 3.0
Image to video · Text to video
Starting price $0.0793 / second
By Alibaba
Alibaba's Wan 2.6 makes 5, 10 or 15 second clips at 720p or 1080p from text, a first frame or subjects filmed in your own videos, can split a prompt into timed shots, and takes your own music track.
wan/v2.6/text-to-videoThis model has other modes with their own ids: wan/v2.6/image-to-video.
Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan/v2.6/text-to-video",
"input": {
"prompt": "A young baker'\''s first morning in her own shop. First shot [0-3s]: she unlocks the door at dawn. Second shot [3-5s]: flour dusts the air as she kneads dough, smiling."
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "wan/v2.6/text-to-video", "quote_id": "QUOTE_ID", "input": {"prompt":"A young baker'\''s first morning in her own shop. First shot [0-3s]: she unlocks the door at dawn. Second shot [3-5s]: flour dusts the air as she kneads dough, smiling."}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
promptrequired | string | The text prompt for video generation. Supports Chinese and English, max 1500 characters. For multi-shot videos, use format: 'Overall description. First shot [0-3s] content. Second shot [3-5s] content.' |
audio_url | string (URL) | URL of the audio to use as the background music. Must be publicly accessible. Limit handling: If the audio duration exceeds the duration value (5, 10, or 15 seconds), the audio is truncated to the first N seconds, and the rest is discarded. If the audio is shorter than the video, the remaining part of the video will be silent. For example, if the audio is 3 seconds long and the video duration is 5 seconds, the first 3 seconds of the output video will have sound, and the last 2 seconds will be silent. - Format: WAV, MP3. - Duration: 3 to 30 s. - File size: Up to 15 MB. |
aspect_ratio | string (enum) | The aspect ratio of the generated video. Wan 2.6 supports additional ratios. |
resolution | string (enum) | Video resolution tier. |
duration | string (enum) | Duration of the generated video in seconds. Choose between 5, 10, or 15 seconds. |
negative_prompt | string | Negative prompt to describe content to avoid. Max 500 characters. |
enable_prompt_expansion | boolean | Whether to enable prompt rewriting using LLM. Improves results for short prompts but increases processing time. |
multi_shots | boolean | When true, enables intelligent multi-shot segmentation for coherent narrative videos. Only active when enable_prompt_expansion is True. Set to false for single-shot generation. |
seed | integer | Random seed for reproducibility. If None, a random seed is chosen. |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
Wan 2.6 renders 5, 10 or 15 seconds in 16:9, 9:16, 1:1, 4:3 or 3:4. With prompt expansion on, multi-shot mode cuts the story into shots; you can also time them yourself in the prompt, for example "First shot [0-3s] ... Second shot [3-5s] ...".
Add a WAV or MP3 of 3 to 30 seconds as background music; it is cut to the clip length, or the clip goes silent where a short track ends. The image mode starts from your picture and keeps multi-shot off unless you turn it on. The reference mode puts people, animals or objects from up to 3 videos into a new 5 or 10 second scene.
Check scene transitions, subject continuity and sound coverage through the ending.