{
  "skills": {
    "entries": {
      "video-prompt-generator": {
        "enabled": true,
        "env": {
          "NANOPHOTO_API_KEY": "your_api_key_here"
        }
      }
    }
  }
}

Other valid ways to provide the key:

Shell: export NANOPHOTO_API_KEY="your_api_key_here"
Tool-specific env config: any runtime that injects NANOPHOTO_API_KEY
OpenClaw config fallback: the bundled script also falls back to ~/.openclaw/openclaw.json at skills.entries.video-prompt-generator.env.NANOPHOTO_API_KEY

Credential declaration summary:

Primary credential: NANOPHOTO_API_KEY
Resolution order in the bundled script: --api-key → NANOPHOTO_API_KEY environment variable → ~/.openclaw/openclaw.json skill env
No unrelated credentials are required

Recommended workflow

Collect the user's topic or scene idea.
Decide whether the prompt is for textToVideo or imageToVideo.
Choose a technique, duration, locale, and optional model override.
For image-to-video mode, require one to three public image URLs.
Run the bundled script or call the API directly.
Return the generated prompt text exactly as produced unless the user asks for adaptation or rewriting.

Parameter guidance

topic
- Required
- Maximum 500 characters
- Keep it specific enough to imply subject, mood, or motion
mode
- textToVideo: default
- imageToVideo: requires public imageUrls
technique
- Default: montage
- Choose the technique that best matches the intended visual language
duration
- 10
- 15
locale
- Default: en
- Supported: en, zh, zh-TW, ja, ko, es, fr, de, pt, ru, ar

Preferred command

Use the bundled script for reliable prompt generation:

Text-to-video prompt

python3 scripts/video_prompt_generator.py \
  --topic "A serene Japanese garden with cherry blossoms falling into a koi pond" \
  --mode textToVideo \
  --technique slow-motion \
  --duration 15 \
  --locale en

Image-to-video prompt

python3 scripts/video_prompt_generator.py \
  --topic "Animate this landscape with gentle wind and floating clouds" \
  --mode imageToVideo \
  --technique long-take \
  --duration 10 \
  --locale en \
  --image-url https://example.com/landscape.jpg

The script resolves credentials in this order: --api-key, then NANOPHOTO_API_KEY from the environment, then ~/.openclaw/openclaw.json at skills.entries.video-prompt-generator.env.NANOPHOTO_API_KEY.

Output behavior

The API returns streaming text, but the bundled script prints the final assembled prompt text
Return the prompt directly when the user asked for prompt generation
If the user wants editing or localization after generation, transform the generated prompt in a second step instead of changing API parameters retroactively

Manual API call

curl -X POST "https://nanophoto.ai/api/sora-2/generate-prompt" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NANOPHOTO_API_KEY" \
  --data-raw '{
    "topic": "A futuristic cityscape at sunset with flying vehicles and neon lights",
    "technique": "aerial-view",
    "duration": 15,
    "locale": "en"
  }'

Error handling

errorCode	Cause	Action
`LOGIN_REQUIRED`	Invalid or missing API key	Verify key at https://nanophoto.ai/settings/apikeys
`API_KEY_RATE_LIMIT_EXCEEDED`	Rate limit exceeded	Wait and retry
`INSUFFICIENT_CREDITS`	Not enough credits	Top up credits
`INVALID_INPUT`	Missing or invalid topic	Ask for a valid topic under 500 characters

Bundled files

scripts/video_prompt_generator.py: generate a prompt from a topic using the NanoPhoto Prompt Generator API
references/api.md: condensed API reference, inputs, and error behavior

video-prompt-generator

Video Prompt Generator

Prerequisites