WaveSpeedAI APIVeedVeed Fabric 1.0

Veed Fabric 1.0

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

ResolutionPrice per 5 secondsExample (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

  1. 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.
  2. 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.
  3. Select resolution

    • Choose 480p for lightweight clips or 720p for sharper output.
  4. Run

    • Click Run to start the job. You’ll receive a job ID; the UI will show progress.
  5. 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

ParameterTypeRequiredDefaultRangeDescription
audiostringYes--The audio for generating the output.
imagestringYes-The image for generating the output.
resolutionstringNo480p480p, 720pThe resolution of the output video.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsstringArray of URLs to the generated content (empty when status is not completed).
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.