Browse ModelsSkywork AISkywork AI Skyreels V3 Extend Video Cutshot

Skywork Ai Skyreels V3 Extend Video Cutshot

Skywork Ai Skyreels V3 Extend Video Cutshot

Playground

Try it on WavespeedAI!

SkyReels V3 Extend Video Cutshot is a fast AI video extension model that extends an existing video with a cinematic cutshot transition guided by a text prompt. Ready-to-use REST inference API for scene transitions, storytelling sequences, advertising creatives, social media clips, product videos, and professional video generation workflows with simple integration, no coldstarts, and affordable pricing.

Features

Skywork AI SkyReels V3 Extend Video Cutshot

Skywork AI SkyReels V3 Extend Video Cutshot continues an existing video clip with newly generated footage while allowing control over shot transition behavior through cut_type. Upload a source video, describe how the scene should evolve, and generate an extension that continues the story with smoother or more intentional cut-style progression.


Why Choose This?

  • Video continuation with shot control Extend an existing clip while influencing how the continuation is cut or transitioned.

  • Prompt-guided scene evolution Describe what should happen next using natural language.

  • Cut-style flexibility Use cut_type to control how the model handles the continuation shot structure.

  • Simple workflow Upload one video, write a prompt, choose cut behavior and duration, then generate the extension.

  • Production-ready API Suitable for scene continuation, short-form storytelling, product demos, and creative editing workflows.


Parameters

ParameterRequiredDescription
promptYesText description of how the video should continue.
videoYesSource video to extend.
cut_typeNoShot transition or cut behavior for the extension. Default: Auto.
durationNoExtension duration in seconds. Default: 5.

How to Use

  1. Upload your source video — provide the clip you want to continue.
  2. Write your prompt — describe what should happen next in the scene.
  3. Choose cut type (optional) — use Auto or another supported cut mode to guide the transition style.
  4. Set duration (optional) — choose how long the extension should be.
  5. Submit — run the model and download the extended video.

Example Prompt

The woman was engrossed in reading when, amidst a thunderstorm outside, all the lights inside suddenly went out.


Pricing

Pricing is based on duration.

DurationCost
5s$0.20
10s$0.40
15s$0.60

Billing Rules

  • Base price is $0.20 per 5 seconds
  • Pricing scales linearly with duration
  • Total price = $0.20 × duration / 5
  • cut_type does not affect pricing

Best Use Cases

  • Scene continuation — Extend an existing shot into the next beat of the story.
  • Shot-aware storytelling — Control how the continuation feels from a transition or cut perspective.
  • Product demos — Continue a product interaction with more structured shot progression.
  • Creative prototyping — Test alternate continuations with different cut behaviors.
  • Short-form editing — Build longer sequences from shorter source clips.

Pro Tips

  • Keep the prompt focused on what should happen next in the scene.
  • Use Auto when you want the model to choose the most natural continuation.
  • Try different cut_type settings when pacing or shot feel matters.
  • Start with shorter durations to validate the continuation before generating longer results.
  • Use a clear source video so the extension has a stronger visual anchor.

Notes

  • prompt and video are required.
  • cut_type defaults to Auto.
  • duration defaults to 5.
  • Pricing depends only on duration.

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/skywork-ai/skyreels-v3/extend-video-cutshot" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "cut_type": "Auto",
    "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-Text prompt describing the scene, action, camera, or avatar behavior.
videostringYes-Input video URL.
cut_typestringNoAutoAuto, Cut-In, Cut-Out, Shot/Reverse Shot, Multi-Angle, Cut AwayCutshot transition type.
durationintegerNo55 ~ 10Generated or extended video duration 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.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.
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.