API docs / Video models

Seedance 1.5 Pro API

Generates videos with synchronized audio from text prompts, creating cinema-quality content with precise lip-syncing and cinematic camera movements. Uses a dual-branch architecture that produces audio and video simultaneously, ensuring perfect synchronization between sound and visuals. Supports multiple languages and dialects including English, Mandarin Chinese, Japanese, Korean, Spanish, Portuguese, Indonesian, Cantonese, and Sichuanese with accurate lip-sync. Creates professional videos with coherent narratives, character consistency across multiple scenes, and complex camera techniques like dolly zooms, tracking shots, pan, tilt, zoom, truck, and orbit movements. Capable of image-to-video generation with optional last frame control. Generates ambient sounds, character voices with emotional expression, and background music that matches the scene mood. Maintains background stability while subjects move, preventing common warping effects. Supports video durations from 2 to 12 seconds at 24fps with multiple aspect ratios including 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, and 9:21.

Model id
bytedance/seedance-1.5-pro
Provider
Bytedance
Output
Video
Price
From 91 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": "bytedance/seedance-1.5-pro". 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": "bytedance/seedance-1.5-pro",
  "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
promptrequiredstring

Text prompt for video generation

first_framearray of URLs

Input image for image-to-video generation

Up to 1 files · Accepts image/*

last_framearray of URLs

Input image for last frame generation. This only works if an image start frame is given too.

Up to 1 files · Accepts image/*

aspect_ratiostring

One of: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, 9:21

resolutionstring

Output video resolution. 480p is fastest, 720p balances quality and cost, and 1080p provides the highest detail.

Default: 720p

One of: 480p, 720p, 1080p

duration_secondsnumber

Video duration in seconds

Default: 5

Min 4 · Max 12

generate_audioboolean

Generate audio synchronized with the video. When enabled, the model outputs a video with audio that matches the visuals.

Default: true

fpsnumber

One of: 24

seednumber

Random seed. Set for reproducible generation

camera_fixedboolean

Whether to fix camera position

Default: false