Skip to main content

Seedance 2.5 video editing takes a 4–30 second clip and one plain instruction, then rebuilds the footage with that change while the cast, the camera path and the timing of the source stay in place.

From $0.204/s

Workbench

Input

Video editing
Write the change first, then what must stay put. Call the source clip @Video1, reference stills @Image1, @Image2 and reference audio @Audio1, numbered in upload order; Seedance 2.5 follows one clear instruction better than a long list of edits. at least 1 characters
0/30

Drop files or media links, paste, or browse · Up to 30 files · Max 10 MB · JPG · PNG · WEBP · GIF

0 / 30 files
Optional: up to 30 stills that show the target look — a garment, a prop, a face, a set or a palette. Say in the prompt which @Image goes where; extra stills do not change the Seedance 2.5 price. at least 1 items · at most 30 items
affects price1/1

Drop a video here, or browse · 1 file · Max 90 MB · MP4

  • 1
1 / 1 files
Upload the Seedance 2.5 source as MP4, 4 to 30 seconds long; clips outside that range are refused before any charge. The edit comes back at the source's length and aspect ratio. at least 1 characters
0/10

Drop an audio file here, or browse · Up to 10 files · Max 90 MB · MP3 · WAV

0 / 10 files
Optional: up to 10 clips of 2–30 seconds each, 30 seconds combined, that steer the new soundtrack toward a voice, beat or mood. They only matter while generate_audio is on and add nothing to the bill. at least 1 items · at most 10 items
affects price
Seedance 2.5 renders the edit at 480p, 720p (default) or 1080p. Each step up raises the per-second rate, and no setting recovers detail the source never had.
Generate audioaffects price
On by default: Seedance 2.5 writes a fresh soundtrack that fits the edited picture. Switched off, the edit comes back silent — the source clip's own audio is not carried over, so add it back in post if you need it.
Output format
MP4MOV
mp4 by default, or mov for editing suites that prefer it; the container has no effect on what a Seedance 2.5 edit costs.
Return last frame
Also returns the edited clip's closing frame as a separate image, handy as the opening still of a follow-up Seedance 2.5 shot. Off by default.
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run

Related models and next tasks

Missing the model you need?

30-SECOND VIDEO API WITH SOUND

Text, opening images and multimodal references, plus video continuation: up to thirty seconds, native 4K from text or an image, with generated sound.

Made with Seedance 2.5

  • 5s
  • 4s
  • 4s
  • Seedance 2.5 image-to-video, 5 seconds at 720p, 16:9, audio generated with the picture.
    5s
  • Seedance 2.5 image-to-video, 5 seconds at 720p, 3:4, audio generated with the picture.
    5s
  • Seedance 2.5 text-to-video, 5 seconds at 720p, 16:9, audio generated with the picture.
    5s
  • Seedance 2.5 text-to-video, 5 seconds at 720p, 16:9. Grainy monochrome on a loose handheld drift, with audio generated alongside the picture.
    5s
  • 10s
  • 6s
  • 10s

Key numbers

Clip length
4–30S
Choose 4–30 whole seconds with duration_seconds, default 5, and leave time for both the main action and its conclusion in your Seedance 2.5 shot plan.
Top resolution
4K
resolution steps through 480p, 720p, 1080p and native 4k (text and image modes). 720p is the default.
Reference stills
30
reference_image_urls carries up to 30 images into a single shot.
Clips + tracks
10 + 10
Up to 10 reference videos and 10 reference audio tracks, 2–30s each.
Sound included
AUDIO
generate_audio is on by default: room tone, effects and voice, in sync.
Endpoints
4
text-to-video · image-to-video · reference-to-video · video-extend

What it does

Sound with the picture

The sound comes back in the same file as the picture

Seedance 2.5 gives a planned scene up to 30 seconds to develop, with text, still-image and multimodal-reference workflows rather than a single input format.

Casting from your own stills

Thirty references, one shot

Seedance 2.5 reference-to-video separates visual identity from performance guidance: assign each image, video and audio reference a clear role in the written brief.

Open and close on purpose

First frame, last frame, thirty seconds between

Seedance 2.5 creates sound alongside the video when generate_audio is true, its default; separate dialogue, action sounds and ambience in the brief so their timing is clear.

Before you spend

All modes

SpicyAPI adds no content review to Seedance 2.5, but the model can still reject requests under its own checks; the separate [Seedance 2.5 Spicy](/models/seedance-2-5-spicy) page documents its NSFW positioning. Before sending Seedance 2.5 a cast, product or soundtrack, confirm the relevant licenses and adult participants’ consent; do not use non-consensual material or deceptive impersonation.

Text to video

Use Seedance 2.5 text-to-video to develop a scene before its visual assets exist; set out the subject, the action sequence, camera movement and intended sound. Plan the Seedance 2.5 scene in consecutive time ranges, with one visible event per range; reference mode and text mode require a prompt, while image mode can infer motion without it.

Image to video

An approved opening image establishes the composition for Seedance 2.5 image-to-video; describe the movement that should follow and inspect how the original design holds through the shot. The image-to-video task accepts last_image_url with image_url; prepare compatible framing at both ends and describe the action connecting them, without expecting a guaranteed seamless loop.

Reference to video

Seedance 2.5 reference-to-video separates visual identity from performance guidance: assign each image, video and audio reference a clear role in the written brief. Up to 10 video references can guide Seedance 2.5 motion, each 2–30 seconds with 30 seconds total; their measured duration is added to the generated duration for billing.

Video editing

Seedance 2.5 video-edit needs a source clip of 4–30 seconds and returns it at the same length; with generate_audio off the result carries no audio track, so the original sound has to be restored in post.

Where it fits

  • Bar, club and backstage scenes

    Seedance 2.5 creates sound alongside the video when generate_audio is true, its default; separate dialogue, action sounds and ambience in the brief so their timing is clear.

  • Uncensored shorts, couples included

    Use Seedance 2.5 text-to-video to develop a scene before its visual assets exist; set out the subject, the action sequence, camera movement and intended sound.

  • Product films that start from the packshot

    An approved opening image establishes the composition for Seedance 2.5 image-to-video; describe the movement that should follow and inspect how the original design holds through the shot.

  • Series characters who stay the same person

    Seedance 2.5 reference-to-video separates visual identity from performance guidance: assign each image, video and audio reference a clear role in the written brief.

Model reference

Seedance 2.5 API reference

Seedance 2.5 API specifications

Endpoints
text-to-video · image-to-video · reference-to-video · video-extend · video-edit
Clip length
4–30 s · default: 5 s
Resolution
480p, 720p (default), 1080p, 4k (text and image modes)
Aspect ratio
21:9, 16:9, 4:3, 1:1, 3:4, 9:16, adaptive (default); adaptive only on image-to-video
Audio
generate_audio: true · generated audio
References
Up to 30 images, 10 videos, 10 audio tracks — reference-to-video only
Output
MP4 (default) or MOV

How to call the Seedance 2.5 API

  1. What is the Seedance 2.5 API designed for

    Seedance 2.5 gives a planned scene up to 30 seconds to develop, with text, still-image and multimodal-reference workflows rather than a single input format.

  2. How should I write a Seedance 2.5 prompt

    Plan the Seedance 2.5 scene in consecutive time ranges, with one visible event per range; reference mode and text mode require a prompt, while image mode can infer motion without it.

  3. How do I retrieve my Seedance 2.5 result

    Submit the Seedance 2.5 job with an Idempotency-Key and keep its task identifier for polling; after a connection loss, check that identifier before requesting another render.

The short version

Seedance 2.5 gives a planned scene up to 30 seconds to develop, with text, still-image and multimodal-reference workflows rather than a single input format. For Seedance 2.5, output duration and resolution determine the estimate, with reference-video duration also counted in reference mode; inspect the current quote for the exact request. The audio setting also selects a Seedance 2.5 rate tier. Choose the base Seedance 2.5 workflows for written shot plans or multiple reference assets; the separate Spicy family focuses on an opening image and its continuation.

Seedance 2.5 API questions