>docs/api/text-to-video

Text-to-Video API

Generate high-quality videos from text prompts using the nohuman-x33 model. Supports durations of 5 or 10 seconds, multiple aspect ratios, optional audio generation, and CFG scale control. Generation is asynchronous -- submit a request and poll for results.

# Generate Endpoint

POST/v1/videos/generate

Generate a video from a text prompt. Returns a generation ID and poll URL for checking status.

Parameters

Name	Type	Required	Description
`prompt`	string	required	The text prompt describing the video to generate. Be descriptive for best results.
`mode`	string	optional ("fast")	Generation mode. "fast" for faster generation, "hq" for higher quality output.
`negative_prompt`	string	optional	Describe what you do not want in the video (e.g., "blurry, low quality, text overlays").
`aspect_ratio`	string	optional ("16:9")	Output aspect ratio. Options: "16:9", "9:16", "1:1".
`duration`	number	optional (5)	Video duration in seconds. Options: 5 or 10.
`cfg_scale`	number	optional (0.5)	Classifier-free guidance scale. Range: 0 to 1. Higher values follow the prompt more closely.
`sound`	boolean	optional (true)	Enable audio generation for the output video. When true, the model generates synchronized audio.

Response

{
  "id": "gen_a1b2c3d4e5f6",
  "model": "nohuman-x33",
  "status": "created",
  "poll_url": "/v1/videos/generations/gen_a1b2c3d4e5f6"
}

# Poll Endpoint

GET/v1/videos/generations/{id}

Check the status of a video generation task. When status is completed, the result field contains the video URL.

Parameters

Name	Type	Required	Description
`id`	string	required	The generation task ID returned by the generate endpoint.

Response

// Processing:
{
  "id": "gen_a1b2c3d4e5f6",
  "model": "nohuman-x33",
  "status": "processing"
}

// Completed:
{
  "id": "gen_a1b2c3d4e5f6",
  "model": "nohuman-x33",
  "status": "completed",
  "result": {
    "url": "https://cdn.nohuman.studio/v/gen_a1b2c3d4.mp4",
    "format": "mp4"
  }
}

NOTE

Poll every 5 seconds. Typical generation time is 30-120 seconds depending on duration. Statuses: created → processing → completed or failed.

# Code Examples

Generate and Poll

"code-comment"># 1. Submit generation request
curl -X POST https:"code-comment">//api.nohuman.studio/v1/videos/generate \
  -H "Authorization: Bearer $NOHUMAN_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A woman walks through a neon-lit alley in cyberpunk Tokyo, cinematic lighting, rain reflections",
    "duration": 10,
    "aspect_ratio": "16:9",
    "cfg_scale": 0.7,
    "sound": true,
    "negative_prompt": "blurry, low quality"
  }'

"code-comment"># 2. Poll for results (replace {id} with actual generation ID)
curl https:"code-comment">//api.nohuman.studio/v1/videos/generations/{id} \
  -H "Authorization: Bearer $NOHUMAN_KEY"

# Rate Limits & Pricing

Metric	Value
T2V Fast 5s	$0.47
T2V Fast 10s	$0.94
T2V HQ 5s	$0.94
T2V HQ 10s	$1.87
Durations	5s, 10s
Aspect ratios	16:9, 9:16, 1:1
Typical generation time	30-120 seconds

See Pricing for full rate limit tiers and billing details.

# Error Responses

{
  "error": "invalid_request",
  "message": "Invalid request parameters."
}

Code	Description
400	Bad request - missing or invalid parameters
401	Unauthorized - invalid or missing API key
429	Rate limit exceeded - too many concurrent requests
500	Internal server error

SYS :: text-to-video/v1 :: endpoint reference