Google VEO3 Fast
Sound on: Google's flagship Veo 3 text to video model, with audio
Features
Veo 3 Fast is the latest generation text-to-video model from Google DeepMind. Unlike other AI video generators, Veo 3 natively synchronizes audio—including dialogue, ambient sounds, sound effects, and music—directly into generated clips, ushering in a new era of AI video with sound.
Key Features
- Text-to-Image & Video: Instantly generate high-fidelity visuals and cinematic videos from your text prompts.
- Native Audio Generation: Add ambient sounds, effects, and dialogue that are naturally synced with the visuals—no post-production required.
- Dialogue & Lip Sync: Create characters that speak your script with accurate lip sync, enabling AI filmmaking and animated storytelling.
- High Prompt Accuracy: Veo 3 delivers consistent, context-aware results grounded in real-world physics and deep prompt understanding.
- Cinematic Quality: Produce videos with smooth motion, realistic effects, and stunning visual quality.
Use Cases
- Marketing & Advertising: Perfect for short ads, product demos, brand intros, and explainer content—with synchronized narration and ambient audio.
- Filmmaking & Storytelling: Empowers creators to make mini-films, short narratives, visual gags, or cinematic snippets, especially with Flow support.
- Education & Training: Useful for safety videos, scientific demonstrations, mechanical process animations, and training content with voiceovers and sound FX.
- Entertainment & Art: Great for generating abstract animations, stylized visuals, sci-fi landscapes, logos, and artistic sequences—all with cinematic audio.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/google/veo3-fast" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"prompt": "A breaking news ident, followed by a TV news presenter excitedly telling us: We interrupt this programme to bring you some breaking news... Veo 3 is now live on Wavespeed. Then she shouts: Let's go! The TV presenter is an epic and cool punk with pink and green hair and a t-shirt that says 'Veo 3 on Wavespeed'",
"aspect_ratio": "16:9",
"duration": 8,
"enable_prompt_expansion": true,
"generate_audio": false
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Text prompt for generation; Positive text prompt; Cannot exceed 2500 characters | |
| aspect_ratio | string | No | 16:9 | - | Video aspect ratio (16:9, 4:3, 1:1, 3:4, 9:16) |
| duration | integer | No | 8 | 8 | Video duration in seconds |
| negative_prompt | string | No | - | Negative prompt for generation | |
| enable_prompt_expansion | boolean | No | true | - | The model automatically optimizes incoming prompts to improve build quality. |
| generate_audio | boolean | No | false | - | Generate audio for the video. |
| seed | integer | No | - | -1 ~ 2147483647 |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Query Parameters
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |