Sign in

v1

latestOpenAPI 3.1.0MIT2026-07-262861121.0 KB

Generate videos using supported text-to-video, image-to-video, and video-to-video models. The response includes a runId and pending status; poll the status endpoint for completion. See the docs for the current model list and required inputs.

post/generate-video

Request body

modelstring required

The video model to use for generation. See the docs for the current model list and required inputs.

promptstring

Text prompt describing the video to generate

scriptstring

Fully-written script for LongStories models (takes precedence over prompt)

conversationUUIDstring

UUID for conversation tracking

projectIdstring

Project identifier for LongStories models

framework'default' | 'emotional_story' | 'product_showcase' | 'tutorial'

Story framework for LongStories models

shortRequestEnhancerboolean

Smart Enhancement: if true, automatically choose better framework and add Director Notes if necessary

targetLengthInWordsinteger

Target length in words for LongStories models (legacy parameter)

targetLengthInSecondsinteger

Target length in seconds (alternative to words)

directorNotesstring

Prompt for the image generation engine (LongStories). Example: 'Warm lighting' or 'Make the first image very impactful'

aspectRatio'9:16' | '16:9'

Video aspect ratio for LongStories

voicestring

Legacy: Voice ID for narration (use voiceoverConfig.voiceId instead)

captionsShowboolean

Legacy: Whether to show captions (use captionsConfig.captionsEnabled instead)

captionsStyle'default' | 'minimal' | 'neon' | 'cinematic' | 'fancy' | 'tiktok' | 'highlight' | 'gradient' | 'instagram' | 'vida' | 'manuscripts'

Legacy: Style for captions (use captionsConfig.captionsStyle instead)

quality'low' | 'medium' | 'high'

Legacy: Video quality (handled by videoConfig now)

musicstring

Legacy: Music track (use musicConfig instead)

aspect_ratio'16:9' | '9:16' | '1:1' | '4:3' | '3:4'

Aspect ratio (supported by select models)

negative_promptstring

Negative prompt to avoid certain elements

cfg_scalenumber

Classifier-free guidance scale

imageDataUrlstring

Base64 data URL of input image for image-to-video models. Aliases image_data_url and image are also accepted and normalized.

imageUrlstring

Public HTTPS URL of the input image (interchangeable with imageDataUrl). The service will prioritize whichever field you supply before falling back to library attachments.

imageAttachmentIdstring

Library attachment ID for input image

videoUrlstring

Public HTTPS URL of the input video (extend/edit/upscale). Preferred field name for source videos.

videoDataUrlstring

Base64 data URL of the input video.

videostring

Alternate video field accepted by select providers.

videoAttachmentIdstring

Library attachment ID for input video.

prompt_optimizerboolean

Whether to optimize the prompt (MiniMax model)

num_inference_stepsinteger

Number of inference steps

pro_modeboolean

Enable pro mode for Hunyuan Video

resolution'720p' | '1080p' | '540p'

Video resolution

frames_per_secondinteger

Frames per second

seedinteger

Optional seed forwarded on model/provider routes that support it. This may improve reproducibility but does not guarantee identical output.

enable_safety_checkerboolean

Enable safety content filtering

showExplicitContentboolean

Allow explicit content (inverse of safety checker)

enable_prompt_expansionboolean

Enable automatic prompt expansion

accelerationboolean

Enable acceleration for faster processing

shiftnumber

Shift parameter for certain models

age_sliderinteger

Age setting for PromptChan model

audioEnabledboolean

Enable audio for PromptChan model

video_quality'Standard' | 'High'

Video quality for PromptChan model

aspect'Portrait' | 'Landscape' | 'Square'

Aspect setting for PromptChan model

Example request

{
  "prompt": "A serene lake at sunset with gentle ripples on the water",
  "directorNotes": "Warm, cozy lighting with focus on people interacting",
  "voice": "pNInz6obpgDQGcFmaJgB",
  "music": "video-creation/music/dramatic_cinematic_score.mp3",
  "negative_prompt": "blur, distort, and low quality",
  "imageDataUrl": "data:image/jpeg;base64,/9j/4AAQ...",
  "imageUrl": "https://images.unsplash.com/photo-1504196606672-aef5c9cefc92?w=1024"
}

Response

Video generation request submitted successfully (asynchronous processing)

runIdstring required

Unique identifier for the video generation request

projectIdstring

Project identifier (for LongStories models)

status'pending' | 'processing' | 'completed' | 'failed' required

Current status of the generation

modelstring required

The model used for generation

costnumber

Cost of the video generation

paymentSourcestring

Payment source used (USD or XNO)

remainingBalancenumber

Remaining balance after the generation

prechargeLabelstring

Provider label for the precharge