Create a new video generation task using the Veo3 AI model.
Capability | Details |
---|---|
Models | • Veo 3 Quality — flagship model, highest fidelity • Veo 3 Fast — cost‑efficient variant (~20 % of Quality pricing) that still delivers strong visual results |
Tasks | • Text → Video • Image → Video (single reference frame) |
Aspect Ratios | Native 16 : 9. We transparently re‑frame to 9 : 16 via a proprietary post‑process, so vertical output is available without extra work on your side. |
Languages | Google’s native support is English‑only; our multilingual prompt pre‑processing extends reliable generation to most major languages. |
Audio Track | All videos ship with background audio by default. In < 5 % of cases Google suppresses audio when the scene is deemed sensitive (e.g. minors). |
Content Governance | Google enforces strict safety filters that often block celebrity or even ordinary‑person photos. We mitigate the majority of these false positives through an optional Intelligent Fallback (see below). |
enableFallback
)Property | Type | Default |
---|---|---|
enableFallback | boolean | false |
enableFallback: true
instructs the platform to reroute eligible failures to the secondary Veo 3 backend, raising completion rates for edge cases.
public_error_minor_upload
public_error_prominent_people_upload
enableFallback
left at false
(default), the errors above surface as HTTP 422 responses and no additional credits are consumed.
enableFallback
parameter, you can enable intelligent fallback functionality. When the primary model encounters specific errors, the system will automatically switch to a backup model to continue generation, improving task success rates.enableFallback: true
, aspect ratio 16:9, and encounter specific errorsAll APIs require authentication via Bearer Token.
Get API Key:
Usage: Add to request header: Authorization: Bearer YOUR_API_KEY
Request successful
The response is of type object
.