ByteDance

ByteDance

Available via API

Seedance 1.5 Pro

Advanced video generation with synchronized audio - voice, sound effects, and background music

Video Generation

Model Guide

About Seedance 1.5 Pro

Advanced video generation with synchronized audio - voice, sound effects, and background music

Overview

Seedance 1.5 Pro is ByteDance's latest video generation model featuring native audio generation capabilities. Unlike previous versions, it can generate videos with synchronized audio including voice, sound effects, and background music - all in a single generation pass. This makes it ideal for creating complete, ready-to-publish video content.

Key Features

  • Native Audio Generation: Generate synchronized voice, sound effects, and background music with your video
  • First + Last Frame Control: Support for both first frame and last frame image inputs for precise video generation
  • Flexible Duration: Generate videos from 4-12 seconds or use auto mode
  • Multiple Aspect Ratios: Support for 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, and adaptive
  • Return Last Frame: Option to return the last frame for creating consecutive video sequences
  • Fast Generation: Optimized for quick turnaround while maintaining quality

Seedance 1.5 Pro vs Seedance Pro Fast

FeatureSeedance 1.5 ProSeedance Pro Fast
Audio GenerationYes (voice, SFX, music)No
Max Resolution720p1080p
First + Last FrameYesFirst frame only
Duration Range4-12s5-10s
Return Last FrameYesNo

Pricing

ResolutionAudioCredits/SecondBest For
480pNo11Drafts, previews
480pYes22Social media shorts
720pNo25Standard content
720pYes50Professional productions

Duration Options

Duration480p (No Audio)480p (With Audio)720p (No Audio)720p (With Audio)
5 seconds55 credits110 credits125 credits250 credits
8 seconds88 credits176 credits200 credits400 credits
10 seconds110 credits220 credits250 credits500 credits
12 seconds132 credits264 credits300 credits600 credits

Use Cases

Social Media Content with Sound

Create engaging TikTok, Instagram Reels, or YouTube Shorts with built-in audio. No need for post-production audio editing.

Product Demonstrations

Generate product videos with ambient sound effects and background music for e-commerce listings.

Animated Storytelling

Transform static images into animated sequences with synchronized voice narration and sound effects.

Video Sequence Creation

Use the return_last_frame feature to create seamless consecutive video segments for longer narratives.

Technical Specifications

SpecificationValue
Max Resolution720p
Frame Rate24 fps
Duration Range4-12 seconds
Input TypesText, Image (1-2 images)
Audio GenerationVoice, SFX, Background Music
Aspect Ratios16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive
Seed Range-1 (random) or 0-4294967295

Input Modes

ModeInputDescription
Text-to-VideoText promptGenerate video from description
Image-to-Video (Single)1 image + textFirst frame driven animation
Image-to-Video (Dual)2 images + textFirst + last frame guided generation

Best Practices

  1. Enable Audio Wisely: Enable audio generation when the content benefits from sound; disable for faster, cheaper generation when audio isn't needed
  2. Use Dual Images for Transitions: Provide both first and last frame images for smoother, more controlled transitions
  3. Describe Audio in Prompts: Include sound descriptions in your prompts for better audio synchronization
  4. Leverage Return Last Frame: Use this feature when creating multi-part video sequences to ensure continuity
  5. Choose Resolution Based on Platform: Use 480p for social media drafts, 720p for final productions

When to Choose Seedance 1.5 Pro

  • You need video with synchronized audio in one generation
  • Creating content for social media that requires sound
  • Building multi-part video sequences with seamless transitions
  • Need first + last frame control for precise animations

When to Use Seedance Pro Fast Instead

  • You need 1080p resolution output
  • Audio is not required or will be added separately
  • Maximum visual quality is the priority over audio integration

Sources

Backend pricing

Rates published by the API.

Model identity, billing unit and every price tier below are read from the backend catalog.

480p · No sound

11

credits / second

= $0.011 USD / second

Official: $0.0128%

generate_audio
false
resolution
480p

480p · With sound

22

credits / second

= $0.022 USD / second

Official: $0.0248%

generate_audio
true
resolution
480p

720p · No sound

25

credits / second

= $0.025 USD / second

Official: $0.0264%

generate_audio
false
resolution
720p

720p · With sound

50

credits / second

= $0.05 USD / second

Official: $0.0524%

generate_audio
true
resolution
720p

1 credit = $0.001 USD. The final deduction returned by the API is authoritative.

generate_audio 默认开启;duration 为 auto 时按 8 秒计费

Back to all models