Skip to main content

Alibaba's Wan 3.0 edits a 1–15 second clip from one instruction — new wardrobe, light, weather or a rewritten line — while the cast, their movement and the camera path carry over at the source's length, from 480p to 1080p with matching sound.

From $0.045/s10% below the publisher's list price

Workbench

Input

Video editing
Open with “Edit the video:” and name the change, then list what must not move. The source is Video 1; extra stills are Image 1, Image 2 and voice or music clips are Audio 1, Audio 2, in upload order. Wan 3.0 reads intent from the wording, so a prompt that only describes a scene can come back as a fresh take inspired by the clip rather than an edit of it. at least 1 characters
0/10

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

0 / 10 files
Optional, up to 10 stills of the look you want — a jacket, a hat, the set dressing. Name each one in the prompt (“the hat from Image 1”); stills never change what a Wan 3.0 edit costs. at least 1 items · at most 10 items
affects price1/1

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

  • 1
1 / 1 files
The clip to edit: an MP4 of 1 to 15 seconds, with each side between 240 and 4096 pixels. Anything outside the 1–15 second range is refused before a charge, and the edit comes back at the same length and aspect ratio as the clip you send. at least 1 characters
0/5

Drop an audio file here, or browse · Up to 5 files · Max 90 MB · MP3 · WAV

0 / 5 files
Optional, up to 5 clips and 15 seconds combined that set a voice, an accent or a music bed for the regenerated soundtrack; point to them as Audio 1, Audio 2. They are not billed. at least 1 items · at most 5 items
affects price
480p, 720p (default) or 1080p. The setting fixes the pixel budget and the per-second rate; the frame shape still follows the source, so a square clip comes back square.
Generate audio
On by default: Wan 3.0 writes a new soundtrack for the edited picture — rain for a rainy night, a new line of dialogue when you ask for one. Off returns the edit with no audio track at all. The price is the same either way.
Seed
Optional integer from 0 to 2147483647. Reusing a seed makes two Wan 3.0 edits easier to compare, but it does not promise identical frames. no lower than 0 · no higher than 2147483647
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?

UNCENSORED VIDEO API

Turn text, a still or ten references into 2 to 30 seconds with sound.

Key numbers

Endpoints
5
Wan 3.0 separates written scenes, opening-frame animation, clip continuation, reference-led creation and editing an existing clip into five endpoints; choose from the material you already have.
Clip length
2–30S
Any whole number of seconds in one request; 5 is the default.
Top resolution
1080P
Wan 3.0 offers 480p, 720p and 1080p here, with 720p selected by default; this choice sets the per-second tier and can also affect waiting time.
Sound
AUDIO
Wan 3.0 generates sound with the picture by default; choose generate_audio=false for a silent new render, without changing the price tier.
References
10+5+5
Up to 10 images plus 5 videos and 5 audio files in one reference call.
Aspect ratios
5
16:9, 9:16, 1:1, 4:3 and 3:4; image-to-video can inherit the source frame.

Before you spend

All modes

For Wan 3.0, request an integer from 2 to 30 seconds, with 5 as the default, or use -1 for a model-chosen length; automatic duration reserves 30 seconds before settlement on the delivered length. Wan 3.0 offers 480p, 720p and 1080p here, with 720p selected by default; this choice sets the per-second tier and can also affect waiting time. For your Wan 3.0 production, secure permission for every uploaded image, clip and voice, check consent and privacy, and have a person approve the final cut before release. Wan 3.0’s content range on SpicyAPI does not remove your obligations concerning adults, consent, rights or lawful use; keep the public-facing examples suitable for a general audience.

Text to video

This is where the uncensored range shows: a two-women kiss in a neon alley came out of wording alone, and the same wording is refused at the content filter on some vendors' models. What text alone will not give you is a specific face or garment — without a reference the model invents both, and reruns drift.

Image to video

The most literal path. Your opening frame pins wardrobe, figure and set so the prompt only has to carry motion. Add last_image_url when the ending matters. Omit aspect_ratio and the clip inherits the source frame's shape; sending a conflicting ratio crops it.

Reference to video

Wan 3.0 reference-to-video assigns different jobs to images, motion clips, sound, a document or a public page, letting a product brief and its visual references guide the same shot. Wan 3.0 reference capacity: 10 images + 5 videos + 5 audio files; video references and audio references each share a separate 15-second total. Wan 3.0 accepts up to 5 motion references of 1–15 seconds each and 15 seconds combined; reference plus output must fit within 30 seconds and both contribute to billed duration. Each MP4 or MOV must be at least 16 fps, 240–4096 px per side, at most 8:1 and 100 MB; generation can reject a clip that passed task acceptance.

What it does

Two-person scenes

Kisses other models refuse

The clip on this page is a single five-second text-to-video run: two women under one umbrella in a neon alley, ending on a kiss. The same wording is refused at the content filter on some vendors' models. Wan 3.0 accepted it, held both faces through the dolly-in, and returned rain on the soundtrack in the same pass.

Sound with the picture

The sound lines up with the picture

Audio generation is on by default, so one request returns one file with footsteps landing on the frame they belong to and rain rising as the camera pushes in. There is no second job to run and no alignment pass afterwards. Switch it off only when you intend to score the shot yourself.

Reference control

Ten images, five clips, five voices

Reference-to-video takes up to ten images, five videos and five audio files in one request, so a face, a wardrobe, a location plate and a voice can all enter the same shot. Say in the prompt what each reference is for; an unlabelled stack gets averaged into something that resembles none of them.

Made with Wan 3.0

  • 5s
  • 5s
  • Wan 3.0 text-to-video sample at 720p: a 5s, 16:9 shot with sound created alongside the picture.
    5s
  • Wan 3.0 drive-in sample: 5s of text-led video in 16:9 at 720p, including generated sound.
    5s
  • 5s
  • 5s
  • 5s
  • 5s
  • 10s
  • 8s
  • 5s
  • 5s
  • 10s

Where it fits

  • Uncensored scenes that get refused elsewhere

    Couples of any gender, a kiss in the rain, two people sharing one frame. Prompts written this plainly are rejected at the content filter on several competing video models. Wan 3.0 runs them, and your own opening frame is the fastest way to get output that matches your wording.

  • Vertical cutdowns at volume

    Set aspect_ratio to 9:16, keep duration at five or six seconds, and sweep the same shot list across seeds. Because the audio bed comes back inside the file, a clip is postable straight out of the API with no music pass, which is what makes a forty-clip week realistic.

  • Product films from one packshot

    Image-to-video takes the packshot as the opening frame and last_image_url as the closing one, so a bottle can turn, catch a highlight and land back on the hero angle inside five seconds. Label text and silhouette survive because both ends of the move are pinned.

  • Character-locked episodic work

    Feed the same face plate and wardrobe stills into reference-to-video for every shot of an episode, reuse one seed and one prompt skeleton, and change only the action line. The cast stays recognisable across a dozen separately rendered clips.

Model reference

Wan 3.0 API reference

Wan 3.0 API specifications

Producer
Alibaba
Published endpoints
text-to-video, image-to-video, video-extend, reference-to-video, video-edit
Clip length
For Wan 3.0, request an integer from 2 to 30 seconds, with 5 as the default, or use -1 for a model-chosen length; automatic duration reserves 30 seconds before settlement on the delivered length.
Resolution
Wan 3.0 offers 480p, 720p and 1080p here, with 720p selected by default; this choice sets the per-second tier and can also affect waiting time.
Aspect ratios
16:9, 9:16, 1:1, 4:3, 3:4
Audio
Wan 3.0 generates sound with the picture by default; choose generate_audio=false for a silent new render, without changing the price tier.
Reference limits
Wan 3.0 reference capacity: 10 images + 5 videos + 5 audio files; video references and audio references each share a separate 15-second total.
Content
Uncensored; no per-request content declaration

How to call the Wan 3.0 API

  1. 1. Pick the endpoint from what you already have

    Wan 3.0 separates written scenes, opening-frame animation, clip continuation, reference-led creation and editing an existing clip into five endpoints; choose from the material you already have.

  2. 2. Write it as subject → action → camera → light and sound

    For Wan 3.0, describe the action and camera timing before adding atmosphere or sound; when references are supplied, identify what Image 1, Video 1 or Audio 1 contributes rather than leaving their roles ambiguous.

  3. 3. Submit asynchronously, then poll or take the callback

    Send the create call with an Idempotency-Key, keep the task id, and either poll it or register a callback URL. Change one field per rerun and hold the seed — that is the only way to tell whether resolution or wording moved the result.

The short version

Wan 3.0 text-to-video gives a written scene room to develop for 2–30 seconds, with picture and optional sound generated together; no image is supplied to establish the cast or set. Wan 3.0 image-to-video starts with your approved composition in image_url; last_image_url can also fix the closing composition while the prompt describes the movement between them. Wan 3.0 reference-to-video assigns different jobs to images, motion clips, sound, a document or a public page, letting a product brief and its visual references guide the same shot. SpicyAPI’s Wan 3.0 extension extracts the final frame of your source, generates a new image-to-video segment and joins the two; the model does not watch the source’s earlier movement. Wan 3.0’s content range on SpicyAPI does not remove your obligations concerning adults, consent, rights or lawful use; keep the public-facing examples suitable for a general audience.

Wan 3.0 API questions

All Wan models22

Video models18