VideoAnonymized

Seedance 1.5 Pro

Seedance 1.5 Pro is ByteDance's native audio-visual joint generation model, delivering synchronized video and sound in one take with strong prompt fidelity and cinematic control.

Maker
ByteDance
Modality
Video + audio
Max duration
12 seconds
Max resolution
1080p

Overview

What is Seedance 1.5 Pro

Seedance 1.5 Pro is ByteDance's text-to-video model that generates synchronized audio and video in a single pass, supporting up to 12-second clips at 1080p with multilingual lip-syncing and cinematic camera motion. Released in December 2025, it excels at prompt-following and integrated sound design.

Running it privately on Venice

On Venice, Seedance 1.5 Pro runs with anonymized privacy — your prompts are not stored or profiled. This means you can generate uncensored, cinematic-quality audio-video content without leaving a trace. The model’s native audio-visual sync is fully preserved, and you pay only per clip, making it ideal for creators who value both privacy and production-ready output.

AnonymizedNo prompt trainingTEE · hardware enclaveEnd-to-end encrypted

Assessment

Strengths and limitations

Strengths
  • Native joint audio-video generation ensures precise lip-syncing and sound-effect timing without post-processing.
  • Strong prompt adherence, especially for camera movements like dolly, pan, and follow shots.
  • Multilingual and multi-dialect support for dialogue generation, including Chinese, English, Japanese, Korean, and Spanish.
  • Cinematic consistency and narrative coherence improved via RLHF and multi-stage training.
  • Efficient inference with over 10× speedup from optimized acceleration framework.
Limitations
  • Max clip length capped at 12 seconds: not suitable for long-form storytelling.
  • 1080p resolution lags behind 4K models like Kling V3 or Veo 3.1.
  • Hands and fine details can lack stability across frames.
  • Proprietary and closed: no open weights or self-hosting options.

Samples

Sample outputs

Generated on Venice with our standard prompt suite — the same prompts we run through every model of this type, so you can judge it like-for-like.

Cinematic landscape

Slow aerial drone shot gliding over a misty mountain valley at golden hour, sunlight piercing clouds onto a winding river, ancient pine forests on either side, ultra-smooth motion, professional color grading, atmospheric haze, 4K

Seamless loop

Calm ocean waves rolling onto a black-sand beach at sunrise, golden light on wet sand, foam dissolving into the shore, a single silhouetted figure at the waterline, smooth continuous forward push, serene cinematic atmosphere

Urban cinematic

A slow tracking shot through a rain-soaked Tokyo street at night, neon reflecting in puddles, steam rising from a food cart, a person with a translucent umbrella, shallow depth of field, teal-and-orange grade, smooth steady camera

Compare every video model on these prompts

Capabilities

What it supports

  • Text to video
  • Native audio generation

Specifications

Datasheet

Maker
ByteDance
Released
December 16, 2025
Architecture
Dual-branch Diffusion Transformer
Resolutions
1080p, 720p, 480p
Clip lengths
4s – 12s
Mode
text-to-video
Aspect ratios
21:9, 16:9, 4:3, 1:1, 3:4, 9:16
Audio
Yes
Prompt limit
3,500 chars
Privacy on Venice
Anonymized — prompts not stored
Available on Venice since
Mar 2026
License
Proprietary

API

Call it from your code

Venice exposes this model through the REST API. Queue a generation with the model id.

curl https://api.venice.ai/api/v1/video/queue \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-1-5-pro-text-to-video-basic",
    "prompt": "Aerial drone shot over a misty mountain valley at golden hour"
  }'

# Use the returned queue_id with https://api.venice.ai/api/v1/video/retrieve.
# Call /video/complete after downloading if needed.

Pricing

What it costs on Venice

Pay per clip on Venice — price scales with resolution and duration (4s–12s), from $0.10.

1080p · 4s
$0.52
Per clip
720p · 4s
$0.23
Per clip
480p · 4s
$0.10
Per clip

New Venice accounts include a free daily allowance and 500 welcome credits — no credit card required.

Alternatives

How it compares

ModelMax resolutionStrongest atOpen weightsPrice (Venice)
Seedance 1.5 Pro1080pPrompt fidelity, multilingual syncNofrom $0.10
Kling O3 Pro4KHigh-res, long clipsNofrom $0.46
Wan 2.7 Enhanced1080pOpen model, stylized outputYesfrom $0.68
MiniMax H3 Enhanced1080pAffordable bulk generationNofrom $0.50

Excels at camera control and synchronized audio-video in a single take.

Use cases

What it is good for

  1. 01Advertising and social media content requiring synchronized voice and visuals.
  2. 02Multilingual explainer videos with accurate lip-syncing.
  3. 03Creative prototyping with cinematic camera control and sound design.
  4. 04AI-generated performances involving singing or dialogue, such as opera or drama snippets.
  5. 05High-volume clip testing for production pipelines with privacy-sensitive data.

Prompting

Getting better results

Be specific about camera motion — use terms like 'dolly in', 'slow pan left', or 'over-the-shoulder shot'.

Include dialogue in quotes and specify language for accurate lip-syncing.

Use start and end frame descriptions to guide motion trajectory and scene composition.

Mention sound effects explicitly — e.g., 'drumbeat', 'crowd cheering' — to trigger native audio generation.

Version history

Seedance 1.0
2024

Initial release focused on motion stability.

Seedance 1.5 Pro
2025-12

Current — adds native audio, lip-sync, and cinematic control.

FAQ

Frequently asked questions

Seedance 1.5 Pro is ByteDance's text-to-video model that generates synchronized audio and video in a single pass, supporting up to 12-second clips at 1080p with multilingual lip-syncing and cinematic camera motion. Released in December 2025, it excels at prompt-following and integrated sound design.

On Venice, pricing starts at $0.10 per clip for 480p at 4 seconds, scaling with resolution and duration. A 1080p 4-second clip costs $0.52. You pay per generation with no subscription.

No. Seedance 1.5 Pro is a proprietary model developed by ByteDance. It is not open source, and there are no public weights available for self-hosting or fine-tuning.

Yes. It natively generates synchronized audio, including speech, dialogue, and sound effects, directly from the text prompt — no separate dubbing step is needed.

It supports 480p, 720p, and 1080p output resolutions, with aspect ratios including 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16.

Yes. It supports multilingual lip-syncing for Chinese, English, Japanese, Korean, Spanish, and several dialects, with high precision in audio-visual alignment.

Seedance 1.5 Pro excels at prompt fidelity and native audio-video sync, while Kling O3 Pro offers 4K resolution and longer clips. Choose Seedance for cinematic storytelling with sound; Kling for higher fidelity visuals.

Up to 12 seconds. It supports clip lengths from 4 to 12 seconds in one-second increments, making it ideal for short-form content like ads or social videos.

Yes. On Venice, Seedance 1.5 Pro runs uncensored and without content filters, allowing full creative freedom. Prompts are anonymized and not stored.

Run Seedance 1.5 Pro privately

No prompt logging. No data used for training.