Browse ModelsWavespeed AIShort Video Generator

Short Video Generator

Short Video Generator

Playground

Try it on WavespeedAI!

WaveSpeed Short Video Generator creates professional short-form videos from text prompts and optional reference images with native audio, smooth motion, and versatile aspect ratios. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Short Video Generator

Short Video Generator produces professional short-form videos with native audio from text prompts and optional reference images. A versatile all-purpose model for creating polished clips across any format — landscape, vertical, or classic — with cinematic motion, realistic physics, and expressive character performance.


Why Choose This?

  • All-Purpose Short Video One model for every short-form need: ads, social posts, product demos, explainers, teasers, and more. No specialized pipeline required.

  • Native Audio Every video includes synchronized sound — ambient effects, background music, and dialogue with accurate lip-sync. Ready to publish without audio post-production.

  • Cinematic Motion Smooth, natural movement with professional camera work — tracking shots, dolly moves, rack focus, and handheld feel that elevate short-form content to broadcast quality.

  • Real-World Physics Objects interact naturally with proper weight, momentum, and collision. Fluid dynamics and realistic inertia make every scene believable.

  • Reference Image Support Upload up to 4 images to guide character appearance, product details, brand aesthetics, or scene composition for consistent results.

  • Every Aspect Ratio 16:9 for YouTube and web, 9:16 for TikTok and Reels, 4:3 and 3:4 for classic and editorial formats.


Parameters

ParameterRequiredDescription
promptYesDescribe the scene, action, and mood for the video
imagesNoUp to 4 reference images for style, character, or brand guide
aspect_ratioNo16:9 (default), 9:16, 4:3, or 3:4
durationNo5 (default), 10, or 15 seconds

How to Use

  1. Write your prompt — describe the scene with detail: environment, characters, action, lighting, and mood.
  2. Add reference images (optional) — upload product photos, character headshots, or style references.
  3. Select aspect ratio — pick the format for your target platform or use case.
  4. Set duration — 5s for bumpers and hooks, 10s for standard clips, 15s for mini-narratives.
  5. Generate — submit and receive a polished video with synchronized audio.

Pricing

DurationCost
5 s$0.80
10 s$1.60
15 s$2.40

Billing Rules

  • Rate: $0.80 per 5 seconds
  • All aspect ratios are the same price
  • Reference images do not affect pricing

Best Use Cases

  • Marketing & Ads — Generate high-converting video ads with product reference images for brand consistency.
  • Social Media — Produce platform-ready content for any social channel in the right aspect ratio.
  • Product Demos — Showcase features and benefits with professional motion and lighting.
  • Explainer Clips — Turn concepts into visual demonstrations with clear, engaging motion.
  • Event Teasers — Create anticipation with dramatic, cinematic short clips.
  • E-Commerce — Generate lifestyle product videos at scale from product photos.

Prompt Tips

  • Be descriptive about the scene: Include environment, lighting, time of day, and atmosphere.
  • Specify camera movement: “slow pan across the table”, “tracking shot following the subject”, “static close-up” all work well.
  • Describe the mood: “energetic and upbeat”, “calm and serene”, “dramatic and tense” guide the overall feel.
  • Use reference images strategically: Product shots maintain brand identity; character photos ensure face consistency.
  • Match duration to content: 5s for punchy hooks, 10s for standard content, 15s for story-driven clips.

Notes

  • Prompt is the only required field. Reference images are optional but improve consistency.
  • Native audio is generated automatically with every video.
  • Default aspect ratio is 16:9 (landscape).
  • Duration options: 5, 10, or 15 seconds.

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/short-video-generator" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "aspect_ratio": "16:9",
    "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

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-Describe the scene, action, camera movement, and mood for the video.
imagesarrayNo[]-Optional reference images (up to 4) to guide the visual style, characters, or scene composition.
aspect_ratiostringNo16:916:9, 9:16, 4:3, 3:4The aspect ratio of the generated video.
durationintegerNo55, 10, 15The duration of the generated video in seconds.

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.outputsobjectArray 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.