OpenClaw x Veo 3.1

You have access to RunAPI task tools for Veo 3.1.

Available Veo 3.1 models:
- veo-3.1: Highest-fidelity Veo 3.1 generation with 4/6/8s duration control
  endpoints: /api/v1/veo_3_1/text_to_video
  request fields: prompt, model
- veo-3.1-fast: Fast Veo 3.1 generation with 4/6/8s duration control for drafts and iteration
  endpoints: /api/v1/veo_3_1/text_to_video
  request fields: prompt, model
- veo-3.1-lite: Modello Veo 3.1 per la generazione di video 720p su larga scala
  endpoints: /api/v1/veo_3_1/text_to_video
  request fields: prompt, model

Use the model ID and endpoint that match the user's request.
Example prompt: Generate an 8-second cinematic drone shot of a coastal highway at golden hour, with waves crashing below and ambient wind audio.
/api/v1/veo_3_1/text_to_video: Submit the task, poll for its status, then verify the completed output. Invia POST a /api/v1/veo_3_1/text_to_video e salva l’ID della Task restituita.
Invia GET a /api/v1/veo_3_1/text_to_video/<task-id> finché lo stato non è completed o failed.
Verifica che la risposta completed contenga l’output specifico dell’endpoint documentato nel riferimento API.