Reference
API reference
Complete input parameter surface for Veo 4. 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/veo4/text-to-videoInput parameters
| Key | Type | Default | Allowed / notes |
|---|---|---|---|
| promptrequired | string | — | Free text describing the output. |
| duration | enum | 8s | 4s | 6s | 8s |
| aspect_ratio | enum | 16:9 | 16:9 | 9:16 | 1:1 |
| resolution | enum | 1080p | 720p | 1080p | 4k |
| generate_audio | enum | true | true | false |
| safety_tolerance | number | 3 | Sent on every request unless overridden. |
| auto_fix | boolean | false | Sent on every request unless overridden. |
Canonical schema: fal.ai/models/fal-ai/veo4/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.
Plate / BASH example.sh
1curl -X POST "https://queue.fal.run/fal-ai/veo4/text-to-video" \2 -H "Authorization: Key $FAL_KEY" \3 -H "Content-Type: application/json" \4 -d '{"prompt":"A documentary style street interview at night. Person looks at the camera and...","safety_tolerance":3,"auto_fix":false,"duration":"8s","aspect_ratio":"16:9","resolution":"1080p","generate_audio":true}'