Skip to main content
Generate videos from text prompts using fal.ai (Wan 2.2 models). Enable by including "video_*" in the agent’s allowedTools array.

video_generate — Generate Video

Generate a video from a text prompt and save it as MP4.

Parameters

ParameterTypeRequiredDescription
promptstringyesText prompt describing the video to generate
pathstringyesOutput file path (e.g. output.mp4)
modelstringnofal.ai video model ID (default: fal-ai/wan/v2.2-1.3b/text-to-video)
num_framesnumbernoNumber of frames to generate (default: 81, ~5 seconds at 16fps)
resolutionstringnoVideo resolution as WIDTHxHEIGHT (default: 854x480)
num_inference_stepsnumbernoInference steps — higher is better quality but slower (default: 30)
guidance_scalenumbernoHow closely to follow the prompt (default: 5.0)
seednumbernoRandom seed for reproducible results

Models

ModelQualitySpeed
fal-ai/wan/v2.2-1.3b/text-to-videoGood (default)Faster (1-2 min)
fal-ai/wan/v2.2-a14b/text-to-videoBestSlower (3-5 min)

Returns

Confirmation with file path, size, model used, and generation parameters.

Notes

  • Requires FAL_KEY environment variable or a vault entry (service "fal", key "key")
  • Output is saved as MP4 within the agent’s sandbox
  • Generation time varies from 1-5 minutes depending on model and resolution