MiniMax H3 Open Weights | Try in Video Generator →
Home/Explore/Skywork Ai/Skyreels V3/Video Extend Cutshot

Skyreels V3 Extend Video Cutshot | AI Video Extension

skywork-ai/

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.

video-extend
Input

Idle

$0.2per run·~50 / $10

ExamplesView all

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

Related Models

README

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.

Related Models

Note:This website uses AI models provided by third parties.

Skyreels v3 Video Extend Cutshot API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/skywork-ai/skyreels-v3/video-extend-cutshot with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Skyreels v3 Video Extend Cutshot below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "cut_type": "Auto",
    "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/skywork-ai/skyreels-v3/video-extend-cutshot" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/skywork-ai/skyreels-v3/video-extend-cutshot";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
        "cut_type": "Auto",
        "duration": 5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
    "cut_type": "Auto",
    "duration": 5
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/skywork-ai/skyreels-v3/video-extend-cutshot", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Skyreels v3 Video Extend Cutshot API — Frequently asked questions

What is the Skyreels v3 Video Extend Cutshot API?

Skyreels v3 Video Extend Cutshot is a Skywork Ai model for video extension, exposed as a REST API 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. You can call it programmatically or try it from the playground above.

How do I call the Skyreels v3 Video Extend Cutshot API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/skywork-ai/skywork-ai-skyreels-v3-video-extend-cutshot.

How much does Skyreels v3 Video Extend Cutshot cost per run?

Skyreels v3 Video Extend Cutshot starts at $0.20 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Skyreels v3 Video Extend Cutshot accept?

Key inputs: `prompt`, `video`, `duration`, `cut_type`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/skywork-ai/skywork-ai-skyreels-v3-video-extend-cutshot.

How do I get started with the Skyreels v3 Video Extend Cutshot API?

Sign up for a free WaveSpeedAI account to claim starter credits, copy your API key from /accesskey, then call the endpoint shown in the API tab of the playground. The playground also auto-generates a code sample in Python, JavaScript, or cURL for the parameters you've set.

Can I use Skyreels v3 Video Extend Cutshot outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Skywork Ai). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

Skyreels V3 Extend Video Cutshot | AI Video Extension API on WaveSpeedAI