AI Video Generation
Create AI-generated videos from text prompts or images using Veo 3.1 with duration, aspect ratio, and audio controls.
AI Video Generation Overview
Generate short-form videos from text prompts or images using Google's Veo 3.1 model via fal.ai. Perfect for social media, ads, and content that needs motion.
Available Video Models
- Veo 3.1 Fast (text-to-video) - Generate from text prompts
- Veo 3.1 Fast Image-to-Video - Animate still images
- Veo 3.1 Fast Extend Video - Extend existing videos by ~7 seconds
All Veo models are optimized for fast generation (2-5 minutes) while maintaining high quality.
Video Durations & Pricing
Choose video duration based on platform and budget. Longer videos cost more credits:
- 4 seconds - 20 credits (quick loops, GIFs)
- 6 seconds - 30 credits (Instagram Reels intro, TikTok hooks)
- 8 seconds - 40 credits (full short-form clips)
Start with 4-second videos to test prompts and concepts. Generate longer versions once you're satisfied.
Text-to-Video Generation
Generate videos from text prompts describing the scene, motion, and style you want. The AI creates realistic video clips with camera movement and natural motion.

- Click 'Generate Video' from post editor or Media Library
- Enter detailed prompt describing scene and motion
- Select duration (4s, 6s, or 8s)
- Choose aspect ratio (16:9, 9:16, 1:1)
- Select resolution (720p or 1080p)
- Enable/disable audio generation
- Click 'Generate' - video ready in 2-5 minutes
Writing Video Prompts
Effective video prompts include: Scene description (setting, subjects), Motion description (camera movement, subject actions), Lighting and atmosphere, Style (cinematic, documentary, etc.), Time of day or season.
Example: 'Aerial drone shot flying over a bustling city at sunset, camera slowly ascending, warm golden hour lighting, cinematic style, urban atmosphere with glowing skyscrapers'.
Image-to-Video
Animate still images by uploading an image and describing the motion you want. The AI keeps the image composition while adding movement, making it perfect for bringing product photos or graphics to life.
Example: Upload a product photo and prompt: 'Slow 360-degree rotation, studio lighting, product showcase style'.
Video Extension
Extend existing videos by ~7 seconds (35 credits). Upload a video and the AI continues the motion naturally. Useful for creating longer clips from successful short generations.
Aspect Ratios for Video
- 16:9 (Landscape) - YouTube, LinkedIn, Facebook horizontal
- 9:16 (Vertical) - Instagram Stories/Reels, TikTok, YouTube Shorts
- 1:1 (Square) - Instagram feed, Facebook feed
- 4:5 (Portrait) - Instagram feed optimized
Generate vertical (9:16) videos for maximum engagement on Instagram Reels and TikTok.
Resolution Options
Choose between 720p (HD) and 1080p (Full HD). Both look great on social media. 1080p provides better quality for larger screens but takes slightly longer to generate and uses more storage.
Audio Generation
Enable audio generation to add ambient sounds matching your video. The AI generates contextual audio (wind, water, city sounds, etc.) based on your prompt. Disable for silent videos.
Negative Prompts
Use negative prompts to exclude unwanted elements: 'No text, no watermarks, no people, no blurry footage'. This helps the AI avoid common issues and generate cleaner results.
Thumbnail Generation
Audenci automatically generates thumbnails for your videos, making them easy to browse in the Media Library and use in posts.
Best Practices
- Start with shorter durations to test prompts
- Be specific about camera movement and speed
- Include lighting and atmosphere details
- Use negative prompts to avoid issues
- Generate vertical videos for social media
- Test image-to-video for product animations
- Combine multiple short clips for longer content