Seedance 2.5 (Video-Edit Turbo) is the turbo tier for editing an input video from a natural-language prompt — faster, more affordable high-resolution output while preserving subject identity, composition, and motion. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.
Idle
$0.216per run·~46 / $10
Replace the dog with a sheep, leave all other elements unchanged.
Seedance 2.5 Video Edit Turbo edits an input video from a natural-language prompt. It is the turbo tier for faster, more affordable high-resolution video editing while preserving the subject identity, composition, and motion of the original clip.
Turbo video editing
Optimized for faster and more cost-efficient high-resolution video edits.
Conversational video editing
Describe the change in plain language, and the model applies the edit while keeping the original motion structure.
Subject and motion preservation
Preserve faces, objects, camera movement, and scene composition from the input video.
Multi-reference support
Optionally guide style, character identity, or audio direction with reference images and audio clips.
Native audio synchronization
Generate synchronized audio together with the edited video output.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Describe the edit. |
| video | Yes | Input video URL. Videos longer than 30 seconds are trimmed to 30 seconds; videos shorter than 4 seconds are padded to 4 seconds. |
| reference_images | No | Up to 30 reference images for style, subject identity, or visual guidance. |
| reference_audios | No | Up to 10 reference audio clips for audio guidance. |
| resolution | No | Output resolution: 720p or 1080p. Default: 720p. |
| generate_audio | No | Generate new audio. When false, keep the input video's audio instead. Default: true. |
720p or 1080p. Leave generate_audio on for new audio, or turn it off to keep the input audio.Editing keeps your source video and changes only what you name. Be precise about the scope, and describe the change as from A to B.
Name exactly what to add, remove, or modify — and use an editing trigger word (add, remove, replace, change to, modify) so the intent is unambiguous.
Confine a change to a time range so the rest of the clip is untouched.
Attach images to specify a replacement, and bind each explicitly (see below).
When you attach images, videos, or audio, bind each one explicitly in the prompt by its upload order — @Image 1, @Video 1, @Audio 1 — and say what it's for. Don't rely on labels drawn inside the image itself.
When a reference is already accurate, just point to it — no need to re-describe it in detail.
You can add, remove, or modify audio too.
Positive descriptions work best, but you can suppress subtitles and audio:
| prompt | |
|---|---|
| weak | change the video |
| strong | Replace the red car in the video with a black motorcycle, matching its motion and speed. Keep the road, lighting, and camera movement unchanged. From 2s onward, add faint dust kicked up behind the rear wheel. Keep the original engine audio. |
The price depends on the length of your input video and the output resolution (720p or 1080p):
1080p costs slightly more than 720p for the same length.Default settings (720p, shortest billed length): $0.96 $0.864 per run.
| Input video length | 720p (resolution=720p) | 1080p (resolution=1080p) |
|---|---|---|
| 4 s or shorter (minimum) | ||
| 5 s | ||
| 8 s | ||
| 10 s | ||
| 12 s | ||
| 15 s | ||
| 20 s | ||
| 30 s or longer (maximum) |
720p for lower-cost testing and 1080p for higher-resolution output.generate_audio to false to keep the input video's audio instead.@Image 1, @Image 2, @Audio 1, and similar asset tags to reference uploaded assets in the prompt. Number each type separately, in upload order.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedance-2.5/video-edit-turbo with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Seedance 2.5 Video Edit Turbo below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"resolution": "720p",
"generate_audio": true
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.5/video-edit-turbo" \
-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="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(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' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.5/video-edit-turbo";
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 ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"resolution": "720p",
"generate_audio": true
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${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", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}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",
"resolution": "720p",
"generate_audio": True
}
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/bytedance/seedance-2.5/video-edit-turbo", 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 = 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", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Seedance 2.5 Video Edit Turbo is a ByteDance model for video editing, exposed as a REST API on WaveSpeedAI. Seedance 2.5 (Video-Edit Turbo) is the turbo tier for editing an input video from a natural-language prompt — faster, more affordable high-resolution output while preserving subject identity, composition, and motion. Ready-to-use REST API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
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 Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/bytedance/seedance-2.5/video-edit-turbo.
Seedance 2.5 Video Edit Turbo starts at $0.216 per run or per second. 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.
Key inputs: `prompt`, `video`, `resolution`, `reference_images`, `generate_audio`, `reference_audios`. 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/bytedance/seedance-2.5/video-edit-turbo.
Reported generation time on WaveSpeedAI is around 318 seconds per request. This is an estimate, not a latency guarantee; queue time and input settings can change the total wait. live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (ByteDance). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.