Ai Video Ads

Playground

AI Video Ads generates product advertisement videos. Provide a person photo, product name, and optional product image or script, and AI creates a professional ad video. Ready-to-use REST inference API, no coldstarts, affordable pricing.

Features

AI Video Ads

AI Video Ads generates professional product advertisement videos from a portrait photo and a product name. Upload a person photo, provide the product details, and AI creates a polished spokesperson-style ad video — complete with script, voiceover, and lip-sync.

Why Choose This?

Spokesperson ad generation Turns any portrait into a professional talking-head product advertisement without filming or scripting.
AI-generated script Provide a product name and optional selling points — the model writes and delivers the ad script automatically.
Product image compositing Upload a product photo for more accurate visual integration of the product into the ad.
Multilingual output Generate ads in English, Chinese, Spanish, French, or Portuguese to reach global audiences.
Flexible duration Generate ads from 5 to 15 seconds to fit different ad formats and platforms.

Parameters

Parameter	Required	Description
image	Yes	Portrait photo of the spokesperson (URL or file upload).
product_name	Yes	Name of the product being advertised.
product_image	No	Product photo for more accurate visual compositing in the ad.
text	No	Script reference or selling points for the AI to use when generating the ad.
language	No	Output language: en, zh, es, fr, or pt.
duration	No	Video length in seconds. Range: 5–15. Default: 5.

How to Use

Upload your person photo — a clear, front-facing portrait works best.
Enter the product name — the AI will generate an appropriate ad script around it.
Upload a product image (optional) — improves visual compositing accuracy.
Add text (optional) — provide key selling points or a rough script for the AI to reference.
Select language (optional) — choose en, zh, es, fr, or pt for the output language.
Set duration — choose between 5 and 15 seconds.
Submit — generate, preview, and download your ad video.

Pricing

Duration	Cost
5s	$0.40
10s	$0.80
15s	$1.20

Billing Rules

Rate: $0.08 per second
Duration range: 5–15 seconds

Best Use Cases

E-commerce advertising — Generate quick spokesperson ads for product listings and social media campaigns.
Social media content — Create short-form ad videos for Instagram Reels, TikTok, and YouTube Shorts.
Multilingual campaigns — Produce the same ad in multiple languages without additional filming.
Small business marketing — Professional ad quality without a production crew or studio.
Product launches — Rapidly generate ad variations for A/B testing across different platforms.

Pro Tips

Use a clean, well-lit front-facing portrait with a neutral background for the most professional result.
Provide key selling points in the text field to guide the AI script toward your actual marketing message.
Upload a product image whenever possible — it significantly improves how the product is visually integrated.
Match duration to your target platform: 5s for social ads, 10–15s for more detailed product explanations.

Notes

image and product_name are required fields; all other parameters are optional.
Providing product_image improves compositing accuracy.
text is used as reference for the AI-generated script — it does not need to be a finished script.
Ensure image URLs are publicly accessible if using links rather than direct uploads.
Please ensure your content complies with WaveSpeed AI’s usage policies.

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/ai-video-ads" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "duration": 5
}'

# 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
image	string	Yes		-	Person photo URL (required).
product_name	string	Yes	-	-	Product name (required).
product_image	string	No	-	-	Product photo URL. Provides more accurate compositing when available.
text	string	No	-	-	Script or selling points for LLM reference (optional).
language	string	No	-	en, zh, es, fr, pt	Language of the generated ad script.
duration	integer	No	5	5 ~ 15	The duration of the generated video in seconds.

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	object	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

AI Twerk AI Virtual Outfit Tryon