API docs / Video models
Hunyuan Video API
Generates videos from text descriptions with realistic motion and temporal consistency. Supports various aspect ratios and resolutions up to 1280x1280 pixels, with configurable video lengths from 1 to 200 frames at customizable frame rates. Uses a spatial-temporally compressed latent space approach with large language model text encoding for advanced prompt handling. Features a built-in prompt rewrite system and stable motion generation capabilities. The model is optimized with parallelized GPU processing using context parallel attention for efficient inference.
- Model id
tencent/hunyuan-video- Provider
- tencent
- Output
- Video
- Price
- From 439 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": "tencent/hunyuan-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": "tencent/hunyuan-video",
"input": {
"prompt": "A cat walks on the grass, realistic style"
},
"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
| Name | Type | Details |
|---|---|---|
prompt | string | The prompt to guide the video generation Default: |
duration_seconds | number | Number of frames to generate (must be 4k+1, ex: 49 or 129) Default: Min 1 · Max 200 |
fps | number | Frames per second of the output video Default: Min 1 |
seed | number | Random seed (leave empty for random) |
guidance | number | Guidance scale Default: Min 1 · Max 10 |
steps | number | Number of denoising steps Default: Min 1 |
height | number | Height of the video in pixels (must be divisible by 16) Default: Min 16 · Max 1280 |
width | number | Width of the video in pixels (must be divisible by 16) Default: Min 16 · Max 1280 |