>docs/models

Models

Nohuman is now a Video Agent powered by Seedance 2.0 Turbo. The API keeps one Nohuman endpoint while exposing Seedance-native controls for text-to-video and image-to-video generation.

# seedance-2.0-turbo

Seedance 2.0 Turbo generates cinematic 720p and 1080p videos from text prompts or reference images with native audio-visual synchronization.

Inputs

Text, image URL, references

Duration

4-15s

Resolution

720p, 1080p

Aspect ratios

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

# API Parameters

Parameter	Type	Description
prompt	string	Required scene, action, camera, and mood description
image_url	string	Optional reference image URL; switches request to image-to-video
duration	number	4-15 seconds; defaults to 5
resolution	string	720p or 1080p; defaults to 720p
aspect_ratio	string	16:9, 9:16, 4:3, 3:4, 1:1, or 21:9
reference_images	string[]	Optional style, character, or scene references for text-to-video
reference_videos	string[]	Optional video references for text-to-video; priced separately
reference_audios	string[]	Optional audio references for text-to-video
sound	boolean	Generate native synchronized audio; defaults to true

# Response

// POST /v1/videos/generate
{
  "id": "gen_a1b2c3d4e5f6",
  "model": "seedance-2.0-turbo",
  "status": "created",
  "poll_url": "/v1/videos/generations/gen_a1b2c3d4e5f6"
}

// GET /v1/videos/generations/{id}
{
  "id": "gen_a1b2c3d4e5f6",
  "model": "seedance-2.0-turbo",
  "status": "completed",
  "result": {
    "url": "https://cdn.nohuman.studio/v/gen_a1b2c3d4.mp4",
    "format": "mp4"
  }
}