Bytedance Seedance 2.5 Flash Video Edit API Documentation
Playground
Try it on WaveSpeedAI!Seedance 2.5 Flash (Video-Edit) edits an input video from a natural-language prompt. The reference video drives subject identity, composition, and motion while the model rewrites lighting, style, weather, environment, or specific elements as instructed. Built on ByteDance Seed’s unified multimodal architecture for cinematic, motion-stable output. Ready-to-use REST API, best performance, no coldstarts, affordable pricing.
Features
Seedance 2.5 Flash Video Edit edits an input video from a natural-language prompt. The source video drives subject identity, composition and motion, while your prompt changes what you describe: the setting, the weather, the style, or a subject. Optional reference images and audio bring in a specific subject or soundtrack. Output is 480p or 720p with synchronized audio.
Parameters
| Parameter | Required | Description |
|---|---|---|
| video | Yes | URL of the video to edit. Only the first 30 seconds are used; sources shorter than 4 seconds are billed as 4 seconds. |
| prompt | Yes | Describe the edit. Refer to reference media as @Image 1, @Audio 1 in upload order. |
| reference_images | No | Up to 10 reference image URLs for a subject, object or style to bring into the edit. |
| reference_audios | No | Up to 5 reference audio URLs. |
| resolution | No | 480p or 720p. Default: 720p. |
| generate_audio | No | Generate synchronized audio. Default: true. |
Pricing
Billing counts the source video duration plus the output duration, which is the same length.
| Resolution | Per second of source video |
|---|---|
| 480p | $0.15 |
| 720p | $0.30 |
Example: a 5 second source costs $0.75 at 480p or $1.50 at 720p.
Pro Tips
- Say what should change and what should stay, for example: keep the person and motion, change the street to a snowy night.
- Bind reference media explicitly in the prompt, for example
@Image 1. - Start with a short clip while testing a prompt.
Related Models
- Seedance 2.5 Flash Text-to-Video
- Seedance 2.5 Flash Reference-to-Video
- Seedance 2.5 Video Edit: up to 4K output.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"video": "https://interactive-examples.mdn.mozilla.net/media/cc0-videos/flower.mp4",
"resolution": "720p",
"generate_audio": true
}
JSON
)
# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
--connect-timeout 10 --max-time 60 \
-X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-2.5-flash/video-edit" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}"); then
printf 'Submit failed. %s\n' "${CHECK}" >&2
exit 1
fi
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"
# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
# Transient errors (429, 5xx) are retried, honoring Retry-After.
HTTP_CODE=$(curl --silent --show-error --fail-with-body \
--connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
--output "${BODY_FILE}" --write-out '%{http_code}' \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
case "${HTTP_CODE}" in
2??) ;;
000|429|5??) # dropped connection or temporary error: keep polling
printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
sleep 10; continue ;;
*) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
cat "${BODY_FILE}" >&2; exit 1 ;;
esac
RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted)
printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneRetry temporary errors only while polling, never the submit request. Errors, retries and timeouts
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Describe the edit you want applied to the input video. | |
| video | string | Yes | - | URL of the input video to edit. Videos longer than 30s are trimmed to 30s; videos shorter than 4s are padded to 4s. | |
| reference_images | array<string> | No | - | 0 ~ 10 items | Optional reference image URLs to guide the edit (subject identity, style, etc.). |
| reference_audios | array<string> | No | - | 0 ~ 5 items | Optional reference audio URLs to guide audio generation. |
| resolution | string | No | 720p | 480p, 720p | Output video resolution. |
| generate_audio | boolean | No | true | - | Whether to generate native audio for the edited output. Defaults to true. When set to false, the input video's audio track is preserved on the output instead. |
Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.
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 | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Task status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses. |
| 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 |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.status | string | Status: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses |
| data.created_at | string | ISO timestamp of when the request was created |
| 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 |