Skip to content

veo-video-gen

Target Audience: Marketers, content creators, and business owners producing social video ads, B-roll, LinkedIn shorts, or product demos without a film crew.

  • Area: Marketing
  • Category: video
  • Level: advanced
  • Input: conversation
  • Output: video-script
  • Setup: api-key
  • Roles: Head of Marketing, Content Manager

Generate AI videos using Google Veo 3.1 via Gemini API directly (no inference.sh dependency).

How you ask

  • “Gemini video”
  • “UGC ad”
  • “LinkedIn video short”

Inputs

  • prompt — Prompt used to generate a video from a text prompt only
  • aspect_ratio — Aspect ratio used to generate a video from a text prompt only (969 | 556)
  • prompt — Prompt used to animate a start image, optionally interpolating to an end image
  • image — Start frame (first frame of output)
  • end_image — End frame for interpolation — must be visually similar to start image
  • video_prompt — Video prompt used to veo video with separate OpenAI TTS narration merged via FFmpeg
  • voice_script — Voice script used to veo video with separate OpenAI TTS narration merged via FFmpeg
  • voice — Voice used to veo video with separate OpenAI TTS narration merged via FFmpeg (alloy | echo | fable | onyx | nova | shimmer)

Outputs

  • generated-video (mp4)
  • prefer a permanent directory)