API docs / Video models

Wan 3.0 (Reference to video) API

Carry a character, a style, or a voice across from reference media.

Model id
alibaba/wan-3.0/reference-to-video
Provider
Wan AI
Output
Video
Price
From 88 credits per run, the same as on voor.ai. Options such as length or resolution can change it.

Request

POST https://voor.ai/v1/generations with "model": "alibaba/wan-3.0/reference-to-video". Poll GET /v1/tasks/{id} or receive the signed webhook. See the overview for keys, idempotency, webhooks and errors.

curl https://voor.ai/v1/generations \
  -H "Authorization: Bearer $VOOR_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "alibaba/wan-3.0/reference-to-video",
  "input": {
    "prompt": "A red fox standing in fresh snow at golden hour, soft light"
  },
  "callback_url": "https://example.com/webhooks/voor"
}'

# Then poll the task (or wait for the webhook):
curl https://voor.ai/v1/tasks/TASK_ID \
  -H "Authorization: Bearer $VOOR_API_KEY"

Input parameters

NameTypeDetails
promptstring

Text prompt directing how the reference media is used. Reference media can be addressed positionally, e.g. 'the subject in Image 1 walks past Video 1'.

Up to 5000 characters

reference_imagesarray of URLs

Up to 10 reference image URLs. Upload up to 10 reference images. They are numbered in upload order and can be inserted into the prompt as Image 1, Image 2, and so on.

Up to 10 files · Accepts image/*

reference_videosarray of URLs

Up to 5 reference video URLs totaling at most 15 seconds. Each clip must be at least 16 fps. Combined duration: up to 15s. Upload up to 5 reference videos. They are numbered in upload order and can be inserted into the prompt as Video 1, Video 2, and so on.

Up to 5 files · Accepts video/*

reference_audiosarray of URLs

Up to 5 reference audio URLs totaling at most 15 seconds. Combined duration: up to 15s. Upload up to 5 reference audio files. They are numbered in upload order and can be inserted into the prompt as Audio 1, Audio 2, and so on.

Up to 5 files · Accepts audio/*

aspect_ratiostring

Output aspect ratio, or adaptive selection.

Default: adaptive

One of: adaptive, 16:9, 4:3, 1:1, 3:4, 9:16

resolutionstring

Output video resolution tier.

Default: 480p

One of: 480p, 720p, 1080p

duration_secondsnumber

Output duration in seconds. Set to null for smart duration, which lets the model pick a length from the prompt and reference media.

Default: 5

Min 2 · Max 30

generate_audioboolean

Include generated audio.

Default: true

enhance_promptboolean

Enable intelligent prompt rewriting. Disabling it can save roughly 20-60 seconds of latency but is likely to degrade generation quality.

Default: true

seednumber

Min 0 · Max 2147483647

enable_thinkingboolean

Enable enhanced reasoning before generation.

Default: false