AI models

VideoGen routes every generation request to a pool of current AI models based on internal evals, compliance requirements, and your intent. Browse the image, video, and voice models available in the platform.

How to choose a model

Image models

Generate stills, product shots, thumbnails, and visual assets. Best for content that lives as a single frame.

Video models

Generate short clips with motion, camera work, and native audio. Best for B-roll, product demos, and social content.

Voice models

Generate narration, dialogue, and voiceovers from text. Best for adding a natural-sounding voice track to your videos.

AI video models

Generate short video clips with expressive motion and cinematic style.

• Minimax
  AI video generation with realistic motion and cinematic visuals
  View model → Minimax
• Grok Imagine
  AI video generation for everyday motion clips
  View model → Grok Imagine
• Veo 3
  Professional AI video generation for polished clips
  View model → Veo 3
• Veo 3.1
  Next-generation AI video with improved realism and audio
  View model → Veo 3.1
• Seedance 2.5
  30-second single-pass video with native audio and up to 50 reference inputs
  View model → Seedance 2.5
• Seedance 2.0
  High-quality AI video generation with reference media
  View model → Seedance 2.0
• Sora
  AI video generation for high-fidelity motion
  View model → Sora
• Kling AI
  Cinematic AI video generation with fluid motion and audio
  View model → Kling AI
• Hailuo AI
  Cost-effective AI video with realistic motion
  View model → Hailuo AI
• Hailuo 3.0
  2K AI video with native stereo audio and 15-second clips
  View model → Hailuo 3.0
• Wan AI
  AI video generation with smooth, coherent motion
  View model → Wan AI
• PixVerse V6
  AI video generation with lifelike physics
  View model → PixVerse V6
• Happy Horse 1.1
  Image-to-video with native audio and lip-sync
  View model → Happy Horse 1.1
• FLUX 3
  Multimodal frontier video with native audio, keyframes, and lip-synced dialogue
  View model → FLUX 3
• Grok Imagine 1.5
  Image-to-video with native audio, improved motion, and near-double speed
  View model → Grok Imagine 1.5
• Gemini Omni Flash
  Arena-leading AI video generation with conversational editing
  View model → Gemini Omni Flash

AI image models

Create images, concepts, thumbnails, and visual assets with top AI image models.

• Flux AI
  Fast, high-quality AI image generation and editing
  View model → Flux AI
• GPT Image
  Professional AI image generation and editing
  View model → GPT Image
• GPT Image 2
  Detailed AI image generation and editing with fine text
  View model → GPT Image 2
• Grok Imagine Image
  Aesthetic AI image generation and editing
  View model → Grok Imagine Image
• Krea 2 Turbo
  Fast, high-fidelity AI image generation
  View model → Krea 2 Turbo
• Nano Banana
  AI image generation and editing for visual projects
  View model → Nano Banana
• Nano Banana 2
  State-of-the-art AI image generation and editing
  View model → Nano Banana 2
• Nano Banana Pro
  Pro-grade AI image generation with strong typography
  View model → Nano Banana Pro
• Seedream 4.5
  Unified AI image generation and editing
  View model → Seedream 4.5
• Seedream 5.0
  Design-focused AI image generation with pixel-level editing
  View model → Seedream 5.0

AI voice models

Create natural narration, dialogue, and voiceovers for your videos.

• ElevenLabs
  Realistic AI voiceovers for your videos
  View model → ElevenLabs
• Inworld AI
  Arena-leading AI voiceovers with natural expression
  View model → Inworld AI