Veo 3.1

Model Information

Display Name: Veo 3.1

API Model ID: google/veo-31

Category: Image To Video

Description: Veo 3.1 is Google's most capable video generation model with native synchronized audio. Produces cinematic-quality videos with realistic motion, physics, and sound design. **Key Features:** - Text-to-video and image-to-video generation - Native audio generation (fully synchronized) - Resolutions: 720p, 1080p, 4K - Portrait (9:16) and landscape (16:9) - Duration: 4s, 6s, or 8s - Video extension (up to 20x, 7s increments, 720p) - Up to 3 reference images for content guidance - First/last frame interpolation **Capabilities:** - Cinematic video production - Synchronized sound design and audio - Photorealistic motion and physics - Character animation with consistency - Camera movement simulation - Scene transitions and effects - Image-to-video animation - Video extension and continuation **Best For:** - Professional video production - Marketing and advertising content - Social media video creation - Cinematic storytelling - High-fidelity video with audio **Technical Specs:** - Model ID: veo-3.1-generate-preview - Input: Text prompt, optional reference image - Output: MP4 video with audio - Resolutions: 720p, 1080p, 4K - Duration: 4-8 seconds (extendable) - Audio: Native synchronized generation - API: Google AI predictLongRunning (async) - Status: Preview

How to Use This Model

To use Veo 3.1 via the HInow.ai API, use the model ID: google/veo-31

API Request Example (Image Generation)


POST https://api.hinow.ai/v1/images
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "google/veo-31",
  "prompt": "Your image description here"
}
              

Pricing

  • total: $0.52

Available Parameters

  • aspect_ratio: Video aspect ratio. Default: 16:9 (Options: 16:9, 9:16)
  • resolution: Video resolution. Default: 1080p (Options: 720p, 1080p, 4k)
  • duration: Duration in seconds. Default: 8 (Options: 4, 6, 8)
  • generate_audio: Generate synchronized audio. Default: true (Options: true, false)
  • person_generation: Person generation policy (Options: dont_allow, allow_adult)

Quick Reference

To use this model, set: "model": "google/veo-31"

Featured: Yes

Documentation: https://hinow.ai/models/google/veo-31

API Endpoint: https://api.hinow.ai/v1

Back to Models

Veo 3.1

Featured

google/veo-31

$0.520
per second

About

Veo 3.1 is Google's most capable video generation model with native synchronized audio. Produces cinematic-quality videos with realistic motion, physics, and sound design.

Key Features:

  • Text-to-video and image-to-video generation
  • Native audio generation (fully synchronized)
  • Resolutions: 720p, 1080p, 4K
  • Portrait (9:16) and landscape (16:9)
  • Duration: 4s, 6s, or 8s
  • Video extension (up to 20x, 7s increments, 720p)
  • Up to 3 reference images for content guidance
  • First/last frame interpolation

Capabilities:

  • Cinematic video production
  • Synchronized sound design and audio
  • Photorealistic motion and physics
  • Character animation with consistency
  • Camera movement simulation
  • Scene transitions and effects
  • Image-to-video animation
  • Video extension and continuation

Best For:

  • Professional video production
  • Marketing and advertising content
  • Social media video creation
  • Cinematic storytelling
  • High-fidelity video with audio

Technical Specs:

  • Model ID: veo-3.1-generate-preview
  • Input: Text prompt, optional reference image
  • Output: MP4 video with audio
  • Resolutions: 720p, 1080p, 4K
  • Duration: 4-8 seconds (extendable)
  • Audio: Native synchronized generation
  • API: Google AI predictLongRunning (async)
  • Status: Preview

Capabilities

Image To VideoText To Video

Parameters

aspect_ratio

Video aspect ratio. Default: 16:9

16:99:16
resolution

Video resolution. Default: 1080p

720p1080p4k
duration

Duration in seconds. Default: 8

468
generate_audio

Generate synchronized audio. Default: true

truefalse
person_generation

Person generation policy

dont_allowallow_adult

Code Examples

curl -X POST https://api.hinow.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "google/veo-31",
    "prompt": "A cat playing with a ball",
    "images": ["https://example.com/image.jpg"],
    "parameters": {
      "aspect_ratio": "16:9",
      "resolution": "720p",
      "duration": "4",
      "generate_audio": "true",
      "person_generation": "dont_allow"
    }
  }'