video-generationlisted

# Video Generation Generate videos from text descriptions using Google's Veo model via the `generate_video` tool. ## Setup 1. Enable video generation in Settings UI or set `NOMOS_VIDEO_GENERATION=true` 2. Get a Gemini API key from https://aistudio.google.com/apikey (same key used for image generation) 3. Set `GEMINI_API_KEY` in Settings or environment ## Tool: `generate_video` **Parameters:** - `prompt` (required) — Detailed description of the video to generate - `output_path` (optional) — File path to save the video (defaults to temp directory) - `duration_seconds` (optional) — Video duration in seconds (1-30) **Note:** Video generation is a long-running operation. It typically takes 1-3 minutes to complete. ## Writing Effective Video Prompts Good video prompts describe motion and time, not just a static scene. Include: - **Subject and action**: What is happening, who/what is moving - **Camera work**: Pan, tilt, zoom, tracking shot, static, drone shot, handheld - **Scene setting**: Location, time of day, weather, environment - **Style**: Cinematic, documentary, slow motion, timelapse, animation - **Mood and atmosphere**: Lighting, color grading, emotional tone - **Temporal flow**: What happens first, then next ### Prompt Examples **Simple:** > A drone shot slowly flying over a misty mountain range at sunrise **Cinematic:** > A slow-motion close-up of a coffee cup being filled with espresso, steam rising, warm golden light from a nearby window, shallow depth of