Google Veo3

Google Veo3

Playground

Sound on: Google’s flagship Veo 3 text to video model, with audio

Features

Veo 3 - Google

Veo3 is Google DeepMind’s latest advancement in text-to-video generation, pushing the boundaries of what AI can create from natural language prompts. With native audio generation, improved prompt adherence, and stunning realism, Veo3 is redefining multimedia content creation.

🔥 Key Features

• Text to Image and Video
  Generate high-fidelity visuals with cinematic detail directly from your text prompts.

• Native Audio Generation
  Add ambient noise, sound effects, and dialogue that sync naturally with visuals—no post-production needed.

• Dialogue & Lip-Sync
  Generate characters speaking your script with accurate lip-sync, opening doors to AI filmmaking and animated storytelling.

• Game World Creation
  Build immersive video game environments from just a sentence—Veo3’s spatial and physics understanding is a game-changer.

• High Prompt Accuracy
  Grounded in real-world physics and enhanced by deep prompt comprehension, Veo3 delivers consistent and context-aware outputs.

• Cinematic Quality
  Output videos in stunning quality, complete with smooth motion and realistic effects.

🧠 Built by Google DeepMind

Trained by world-class researchers at Google DeepMind, Veo3 is engineered for creators, developers, and visionaries looking to push the limits of AI-generated content.

✨ Prompting Tips (from Google’s Guide)

To get the best results, try these prompt strategies:

• Shot Composition:
  Close-up, two shot, over-the-shoulder

• Lens & Focus:
  Macro lens, shallow focus, wide-angle lens

• Genre & Style:
  Sci-fi, romantic comedy, action movie

• Camera Motion:
  Zoom shot, dolly shot, tracking shot, pan shot

🎬 Example Prompt

Close up shot (composition) of melting icicles (subject) on a frozen rock wall (context) with cool blue tones (ambiance), zoomed in (camera motion) maintaining close-up detail of water drips (action).

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/google/veo3" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "prompt": "A breaking news ident, followed by a TV news presenter excitedly telling us: We interrupt this programme to bring you some breaking news... Veo 3 is now live on WaveSpeedAI. Then she shouts: Let's go! The TV presenter is an epic and cool punk with pink and green hair and a t-shirt that says 'Veo 3 on WaveSpeedAI'",
    "aspect_ratio": "16:9",
    "duration": 8,
    "resolution": "720p",
    "generate_audio": false,
    "enable_prompt_expansion": true
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"