Reference
API reference
Complete input parameter surface for Kling 3.0 Pro. The canonical schema lives at the model's llms.txt; the table below is derived from it.
Endpoint
Submit a job to the queue endpoint:
POST https://queue.fal.run/fal-ai/kling-video/v3/pro/text-to-videoInput parameters
| Key | Type | Default | Allowed / notes |
|---|---|---|---|
| promptrequired | string | — | Free text describing the output. |
| duration | enum | 5 | 3 | 5 | 8 | 10 | 15 |
| aspect_ratio | enum | 16:9 | 16:9 | 9:16 | 1:1 |
| resolution | enum | 1080p | 720p | 1080p |
| cfg_scale | number | 0.5 | 0 to 1, step 0.05 |
| generate_audio | enum | true | true | false |
Canonical schema: fal.ai/models/fal-ai/kling-video/v3/pro/text-to-video/llms.txt. Anything new shipped by the model vendor appears there first.
Worked example
Minimal request using the defaults above. Swap the prompt for your own; everything else stays optional.
BASH
1curl -X POST "https://queue.fal.run/fal-ai/kling-video/v3/pro/text-to-video" \2 -H "Authorization: Key $FAL_KEY" \3 -H "Content-Type: application/json" \4 -d '{"prompt":"Three-shot sequence. Shot one: wide establishing on a rain-soaked Tokyo alley...","duration":5,"aspect_ratio":"16:9","resolution":"1080p","cfg_scale":0.5,"generate_audio":true}'