Introduction
Send video_url and prompt; reference_image_urls, reference_audio_urls, resolution and generate_audio are optional. The result follows the source clip, so the request has no duration field. With generate_audio off, the original sound of your clip stays in the output.
| Field | Value |
|---|---|
| Input | Video |
| Output | Video |
| Publisher | ByteDance (Seedance 2.5 Flash, speed tier of Seedance 2.5, announced by BytePlus on 12 November 2026) |
| API names | bytedance/seedance-2.5-flash/text-to-video, image-to-video, reference-to-video, video-edit, video-extend |
| Resolution | 480p or 720p (default 720p); 1080p and 4K not supported |
| Clip length | 4–30 whole seconds, default 5; video-edit follows its 4–30 s source |
| Aspect ratio | 16:9 (default), 9:16, 4:3, 3:4, 1:1, 21:9 or adaptive on text and reference requests; image-to-video follows the start image |
| Reference limits | Up to 10 images, 5 clips (30 s in total) and 5 audio files on reference-to-video |
| Reference clip rules | Each clip counts as at least 2 s and needs about 409,600 pixels (854×480 or larger) |
| Edit inputs |
|
| Audio |
|
| Output options | mp4 (default) or mov; watermark off by default; |
| Billing basis | Per second by resolution; reference clips add their seconds; edits bill source seconds; failed generations are free |
| Measured render time | 84 s to about 11 min for 4 s at 480p (13 November 2026 runs) |
Key features & highlights
Flagship workflows at a lower ceiling
Flash keeps the four Seedance 2.5 workflows that fit drafting (text, start and end frames, mixed references, clip editing), drops 1080p and 4K, and adds a video-extend built on its image-to-video mode. BytePlus presents the trade as results close to the flagship at nearly twice the speed. Our 4-second 480p renders took anywhere from 84 seconds to about 11 minutes, so measure speed on your own queue.
Give every upload a job in the prompt
Name uploads by type and order with a space: @Image 1, @Video 1, @Audio 1. With two portraits as @Image 1 and @Image 2 in 16:9, both people appeared together in one elevator scene and kept their faces, hair and clothes. With one image, one clip and one voice file, the clip's street, yellow tram and tracking camera carried over, but the person stayed back to the camera and the face of @Image 1 barely showed.
A sunny street turned into a snowy evening
Both riders, their bikes, the tram and the camera move matched the source frame by frame, and the weather and light changed while nothing else did. That was a 4.0 s clip at 480p with audio off, which also kept the original soundtrack.
One switch decides whose soundtrack you get
generate_audio is on by default and produces speech, effects and ambience with the picture. In video-edit, switching it off keeps the source clip's own track (44.1 kHz in our test), while switching it on generates a new one that can follow @Audio 1. The switch has no effect on the price.
Request parameters
| Parameter | Required | Description |
|---|---|---|
prompt | Yes | Open with the change, then list what must stay: people, clothing, props, movement and the camera move. at least 1 characters · at most 20000 characters |
video_url | Yes | Link to the MP4 you want to edit, 4 to 30 seconds long; anything outside that range is refused before any charge. at least 1 characters |
reference_image_urls | No | Up to 10 optional images that show the target look, such as a garment, a prop or a colour board. at least 1 items · at most 10 items |
reference_audio_urls | No | Up to 5 optional audio files, 30 seconds in total, that steer the soundtrack the model writes toward a voice or a mood. at least 1 items · at most 5 items |
resolution | No | 480p or 720p, default 720p. Settle the wording at 480p, then rerun the approved prompt at 720p; the choice sets the per-second rate applied to the source length. |
generate_audio | No | true (default) writes a new soundtrack for the edited picture, and false keeps your clip's own sound. Default: |
Pricing
Billed per second of the uploaded source clip (4–30 s, rounded up) at the 480p or 720p rate, whatever length the result comes back at. Reference images, reference audio and the audio switch leave the charge unchanged, and a task that fails is not charged.
| Specification | Price |
|---|---|
| $0.18 / second |
| $0.36 / second |
Use cases
Trying a shot plan before a final render
Send a 4-second, 480p, 16:9 prompt that ends with an Audio: line, such as a rain-soaked night crosswalk. Our run returned 854×480 at 24 fps, 4.064 s long, with an AAC stereo track of rain and laughter. Change one phrase and rerun to see what moved.
Restyling footage you already shot
Upload a 4–30 second clip, describe the change, then list what must stay. A sunny street with two cyclists and a tram became a snowy evening in our test, and with generate_audio switched off the original soundtrack came back unchanged.
Character and product mockups
Attach a portrait and a product photo as @Image 1 and @Image 2 and ask for 9:16. Our two-image test returned 480×854 with the man lifting a glass dropper bottle toward the lens, so both references showed up. Use the result to judge the idea before building a polished version.
Looping a portrait animation
Give the same photo as image_url and last_image_url and describe the motion between them. Our potter portrait returned a 562×748 clip of 4.064 s whose opening and closing frames both matched the source pose.
Chaining one shot into the next
Set return_last_frame to true and the MP4 arrives with a JPEG of its closing frame (854×480 at 480p 16:9 in our test). Pass that JPEG as image_url of the next image-to-video request so the following shot begins where the last one stopped.
Prompt guide & pro tips
Choose the endpoint for your input
Use text-to-video for a prompt alone, image-to-video for a start frame, reference-to-video for images, clips or a voice, video-edit for an existing 4–30 second clip, and video-extend to add 4–30 seconds to a clip of up to 60 seconds. All five share the 480p/720p range and the
generate_audioswitch.Send the createTask request
POST to https://api.spicyapi.ai/api/v1/jobs/createTask with the header Authorization: Bearer YOUR_SPICY_API_KEY and the body {"model": "bytedance/seedance-2.5-flash/text-to-video", "input": {"prompt": "A lighthouse keeper climbs a spiral stair at dawn and wipes fog from the lamp glass. Audio: wind, boots on iron.", "
duration_seconds": 4, "resolution": "480p"}}.Poll for the finished clip
The response gives a taskId in state queued. Call GET /api/v1/jobs/recordInfo?taskId=YOUR_TASK_ID, or pass a callBackUrl, until the state is succeeded, then read the MP4 address from output.assets. Field details are in the task guide at docs.spicyapi.ai/docs/tasks.
Change one phrase, then move up
Compare variations at 480p and 4 seconds, altering a single phrase per run. When a take works, rerun it at 720p and your target length, or send the same brief to Seedance 2.5 for 1080p.
What Seedance 2.5 Flash video edit does
Seedance 2.5 Flash video edit is ByteDance's instruction-editing task for its speed-tier video model: upload a clip of 4 to 30 seconds, describe what should look different, and receive it re-rendered at 480p or 720p. Weather, time of day, wardrobe and props are typical targets; the people, their movement and the camera path are what you ask the model to hold.
BytePlus, ByteDance's cloud platform, describes Flash as "results close to flagship Seedance 2.5, with nearly twice the generation speed". Here the audio switch has two jobs: generate_audio: false keeps your clip's own soundtrack, and true writes a new one that can follow an attached voice file.
Request example
This is the snowfall edit from our tests. Send it as POST https://api.spicyapi.ai/api/v1/jobs/createTask with Authorization: Bearer YOUR_SPICY_API_KEY, as the task API guide describes.
{
"model": "bytedance/seedance-2.5-flash/video-edit",
"input": {
"prompt": "Turn the sunny afternoon into a snowy winter evening: fresh snow on the rooftops, balconies and cobblestones, snowflakes drifting through the air and warm light in the windows. Keep both riders, their bikes, their clothes, their movement, the tram and the camera move exactly as in the source video.",
"video_url": "https://example.com/tram-street.mp4",
"resolution": "480p",
"generate_audio": false
}
}
Response example
Submission returns a task ID. Poll GET /api/v1/jobs/recordInfo?taskId=YOUR_TASK_ID or pass callBackUrl; the finished task lists the edited MP4.
{ "code": 200, "msg": "success", "data": { "taskId": "YOUR_TASK_ID", "state": "queued" } }
{ "code": 200, "msg": "success", "data": { "taskId": "YOUR_TASK_ID", "state": "succeeded",
"output": { "assets": [ { "url": "https://example.com/edited-tram-street.mp4" } ] } } }
Parameter table
prompt and video_url are required.
| Parameter | Values / default | What it does |
|---|---|---|
prompt | Required, up to 20,000 characters | The change, then what must stay |
video_url | Required, MP4, 4–30 s | The clip to edit |
reference_image_urls | Up to 10 | Target looks, named @Image 1, @Image 2 |
reference_audio_urls | Up to 5, 30 s in total | Voice or mood, named @Audio 1 |
resolution | 480p or 720p, default 720p | Output size |
generate_audio | Default true | New sound (true) or source sound (false) |
How billing works
The charge follows the clip you upload, not the clip you get back. Source seconds (4 to 30, rounded up) are priced at the rate of the chosen resolution, shown on this page; a 4.0 second source that returns as 3.712 seconds is billed as 4. References and the audio switch change nothing, and a task that fails is not charged.
Tips for good results
- Write the change, then the keep list. One sentence for the change plus a clause naming everything that must survive held up in our runs. Dreamina, ByteDance's creative app, suggests locking identity, wardrobe, camera path and timing first; either order works if both halves are written.
- Name visible consequences. The snowfall prompt lists what snow does in the frame: covered rooftops, flakes in the air, warm window light. A bare "make it winter" names no surfaces.
- Change one thing per pass. Weather and light are one scene change; add a new jacket in a second pass to see which clause did what.
- Pick the sound setting up front. Audio off protects dialogue or music you want to keep. Audio on suits a picture that needs new sound: attach a voice file as @Audio 1 and add an
Audio:line. - Check frame by frame. ByteDance's Seedance 2.5 announcement says complex motion and scenes with several interacting subjects are still improving, so step through busy moments. Reference images ("the jacket from @Image 1") were not part of our runs; try them on a 4-second trim.
What our tests showed
On 13 November 2026 we edited a 4.0 second clip of a sunny street with two cyclists and a tram, twice, at 480p.
| Run | Settings | Result | Submit to finish |
|---|---|---|---|
| Snowfall, sound kept | Snowy-evening prompt, audio off | 854×480, 4.000 s; riders, tram and camera match the source frame by frame, weather and light changed, source soundtrack kept (44.1 kHz) | 3.7 min |
| Snowfall, new voice | Same prompt, voice file as @Audio 1, audio on | 3.712 s; same edit quality; new soundtrack | 7.8 min |
Across all four Flash endpoints that day, 4-second 480p clips took 84 seconds to about 11 minutes. Two edit runs cannot confirm BytePlus's "nearly twice" claim, so plan for minutes and expect longer clips and 720p to take longer.
Limits and errors
- Source length. A clip under 4 or over 30 seconds is rejected at submit with nothing charged. Trim it, or split a long clip and reuse the keep list on each part.
- Result length. There is no duration field. With audio on the result can run slightly short (3.712 s from 4.0 s here); for an exact length, edit with audio off and add sound in your own editor.
- Resolution. 480p and 720p; ByteDance lists 1080p and 4K as unsupported for Flash.
- Model checks. The model applies its own copyright and likeness checks and can decline or soften a request. A blocked task fails without charge: reword it, drop named people or brands, and resubmit.
- Rights and retention. Edit footage and voices you have the right to use. Finished files are kept for 14 days.
When to choose a sibling
- Seedance 2.5 video edit for final delivery above 720p; the flagship edits at up to 1080p. Read its audio note before reusing a setting from here.
- Seedance 2.5 Flash reference-to-video to build a new scene around a clip's camera move (@Video 1) instead of rewriting the clip.
- Seedance 2.5 video extend when the shot must continue past its last frame.
- Seedance 2.0 Fast, the previous-generation fast tier at 480p and 720p, for extend or text, image and reference work.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "bytedance/seedance-2.5-flash/video-edit",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"resolution": "720p",
"video_url": "https://example.com/reference.mp4"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.










