Video Watermark Remover

Playground

The AI Video Watermark Remover is our flagship model designed to remove Sora 2 watermarks, logos, captions, and unwanted text from videos without compromising quality. Supporting a wide range of formats, it’s fast, efficient, and processes with the highest quality. Whether your video is a few seconds or several minutes long, we can handle it all. Our endpoint starts with $0.05 per 5 seconds video and supports a maximum video duration of 10 minutes.

Features

AI Video Watermark Remover

Remove Sora 2 watermarks, logos, captions, lower-thirds, and other unwanted on-screen text—while preserving the original look of your footage. Upload your video and get a clean result with minimal artifacts. If you need upscaling instead, try our AI Video Upscaler. No local setup required!

Why it looks great

Temporal-aware inpainting: avoids flicker, keeps motion stable across frames.
Clean plate reconstruction: rebuilds occluded details (textures, grain, lighting) beneath watermarks and captions.
Smart text/logo targeting: robust to semi-transparent overlays, moving corner bugs, ticker bars, and burned-in subs.
Edge & texture fidelity: preserves edges and fine detail without smearing or over-smoothing.
Adaptive masking: optional user hints accelerate and improve results on complex, fast-moving overlays.

Limits and Performance

Max clip length per job: up to 10 minutes
Processing speed: approximately 5–20 seconds of wall time to process 1 second of video (varies by overlay complexity, resolution, and queue load)

Pricing

Per-second billing with a 5-second minimum. The table below lists prices per 5 seconds for easy comparison.

Task	Cost per 5 seconds
Watermark Removal	$0.05

Billing Rules

Minimum charge: 5 seconds
Per-second rate = (price per 5 seconds) ÷ 5
Billed duration = video length in seconds (rounded up), with a 5-second minimum
Total cost = billed duration × per-second rate

How to Use

Upload video: Upload the video you want to deal with.
Submit the job: Click the Run button.
Preview & download: review the cleaned clip and download it.

Notes

Longer videos will require longer processing times.
Please ensure your video upload format and URL are correct.
The price displayed on the “Run” button is only an estimated reference; the final, accurate price will be based on the actual deduction.

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/wavespeed-ai/video-watermark-remover" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{}'

# 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
video	string	Yes		-	The video for generating the output.

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

Video Upscaler Pro Wan 2.1 14b LoRA Trainer