Nano Banana

Seedance 2.5 — Native 30-Second AI Video with Audio

Seedance 2.5, released by ByteDance Seed on July 31, 2026, generates up to 30 seconds of video with audio in a single pass. It advances long-form storytelling, multimodal reference and editing, and topped Design Arena's Video Arena in August 2026.

  • ByteDance Seedance 2.5
  • Native 30 s in one pass
  • Up to 50 references
  • Text, frames or references
Open the full workspace

More models

Why Seedance 2.5 Is a Great AI Video Generator

Seedance 2.5 is the model for longer, story-driven clips: a full 30-second scene with consistent characters and sound, without stitching short clips together.

  • 30 seconds natively

    A single generation covers a whole scene — no stitching required.

  • Long-form storytelling

    ByteDance focused 2.5 on narratives that hold together over time.

  • Massive reference input

    Combine up to 50 images, video clips and audio files.

  • Leaderboard leader

    It took the top spot on Design Arena's Video Arena shortly after launch.

What Seedance 2.5 can do

  • Text to video up to 1080p

    Describe a whole scene with dialogue and sound.

  • First / last frame

    Pin the opening and closing images.

  • Reference to video

    Mix many references to lock characters, places and sound.

  • 4–30-second clips

    Pick a length from 4 to 30 seconds, with sound generated in the same pass; audio can be switched off.

  • 480p, 720p and 1080p output

    Choose 480p, 720p and 1080p in 6 aspect ratios: 21:9, 16:9, 4:3, 1:1, 3:4 and 9:16.

  • Reference inputs

    Besides a text prompt you can add a first frame and an optional last frame and up to 50 reference files.

Use cases

Starting points you can copy into the generator above.

Use caseGood forExample prompt
Short filmsA complete 30-second scene.

A detective enters a rain-soaked alley, finds a glowing locket, looks up as sirens approach; moody jazz, rain, footsteps

Ads with a storyA mini narrative for a product.

A girl hides a gift behind her back, her father opens it to find the watch from the reference image, he smiles; warm piano

Music videosLonger clips driven by a track.

A singer walks through a field of sunflowers, camera tracks beside her, lyrics matching the reference audio

Character seriesThe same cast across episodes.

The two characters from the references argue over a map on a ship deck, then laugh; wind and creaking wood

Seedance 2.5 in 3 steps

  1. 1

    Describe the shot or add a frame

    Write what happens, how the camera moves and how it should sound. Add a start image or references to lock the look.

  2. 2

    Pick length, resolution and ratio

    Set duration, resolution and aspect ratio and whether to generate audio. The credit cost is shown before you submit.

  3. 3

    Generate and keep your results

    Videos appear in the generator and are saved to My works. Anything that fails is refunded automatically.

X Posts About Seedance 2.5 — Native 30-Second AI Video with Audio

YouTube Videos About Seedance 2.5 — Native 30-Second AI Video with Audio

Frequently asked questions

Up to 30 seconds in a single pass, with sound. Shorter lengths from 4 seconds are available too.

Ready to Tell a Longer Story with Seedance 2.5?

Up to 30 seconds per clip with up to 50 multimodal references, first/last frames and native audio.

Explore All Models
  • Clips up to 30s
  • Native audio
  • Failed outputs refunded