Veed Fabric 1.0
Playground
Try it on WavespeedAI!VEED Fabric 1.0 turns one image into dynamic, talking videos and AI avatars in 480p or 720p (starts at $0.35/5s 480p, $0.7/5s 720p). Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
VEED Fabric 1.0
An image-to-video API that brings a single still image to life as a dynamic, talking video. Ideal for video storytelling, personalized messages, digital avatars, and automated content pipelines.
Why it looks good
- One image + Audio → talking video: Generate lip-synced, expressive clips from a single portrait or character image.
- Natural lip-sync & expressions: Stable mouth–audio alignment and smooth facial transitions with minimal jitter.
- Short creation pipeline: Image + voice → finished video, optimized for batch runs and automation.
- Multi-scenario ready: Explainers, greetings, brand characters, course intros, and support avatars.
Pricing
| Resolution | Price per 5 seconds | Example (10s) | Example (15s) |
|---|---|---|---|
| 480p | $0.35 | $0.70 | $1.05 |
| 720p | $0.70 | $1.40 | $2.10 |
Our endpoint starts at $0.35 per 5 seconds (480p) or $0.70 per 5 seconds (720p) for video generation.
How to use
-
Upload audio
- Add a voice track URL or drag-and-drop a file into the audio field.
- Use clean, paced speech; denoise/EQ if possible.
-
Upload image
- Paste an image URL or drag-and-drop a portrait into the image field.
- Prefer a clear front or body view with even lighting.
-
Select resolution
- Choose 480p for lightweight clips or 720p for sharper output.
-
Run
- Click Run to start the job. You’ll receive a job ID; the UI will show progress.
-
Retrieve & iterate
- Download the result when complete.
- Swap audio or image, or adjust resolution to iterate quickly.
Common use cases
- Digital avatars
- Personalized greetings
- Education snippets
- Social/marketing upgrades (poster → talking video)
- Customer service presenters
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/veed/fabric-1.0" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"resolution": "480p"
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| audio | string | Yes | - | - | The audio for generating the output. |
| image | string | Yes | - | The image for generating the output. | |
| resolution | string | No | 480p | 480p, 720p | The resolution of the output video. |
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 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, the ID of the prediction to get |
| data.model | string | Model ID used for the prediction |
| data.outputs | string | 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.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 |