Seedance 1.5 Pro API

Experience the next evolution in generative media with Seedance 1.5 Pro API. Developed by ByteDance's Seed Team, this model unifies high-fidelity video generation with native audio synthesis, now available for seamless integration through Evolink.

A cat wandering through the city and then going back to sleep

Parameters
duration
5
quality
720p
aspect_ratio
16:9
generate_audio
true
Estimated Cost
10 Credits/s
Total = Base Price × Duration × Quality
Sample Result

No sample available

61 (suggested: 2,000)

Upload 1-2 images (max 10MB each)

Click to upload or drag and drop

Supported formats: JPG, JPEG, PNG, WEBP
Maximum file size: 10MB; Maximum files: 2

5s
4s12s

Generate synchronized audio (voice, sound effects, background music)

Click Generate to see preview

History

Max 20 items

0 running · 0 completed

Your generation history will appear here
$

Pricing

Starting from
$0.010
10 Credits
per second
Guaranteed
99.9% Uptime
Powered by 16 redundant providers

Seedance 1.5 Pro: The Future of Cinematic AI Video

Generate 1080p videos with synchronized audio, precise camera control, and multi-shot consistency. Seedance 1.5 Pro API transforms text and images into professional film sequences.

Seedance 1.5 Pro API cinematic showcase

What can you build with Seedance 1.5 Pro API?

Text-to-Video with Native Sound

Seedance 1.5 Pro API revolutionizes storytelling by generating synchronized audio alongside video. Whether it's dialogue with accurate lip-syncing or immersive ambient soundscapes like crashing waves and bustling city streets, the model creates a cohesive audio-visual experience directly from your text prompts.

Seedance 1.5 Pro API text to video example

Cinematic Image-to-Video Animation

Breathe life into static imagery with Seedance 1.5 Pro API's advanced Image-to-Video capabilities. Turn product photos, concept art, or character portraits into dynamic, high-definition videos. The model intelligently infers motion and depth, allowing you to define start and end frames for precise transitions.

Seedance 1.5 Pro API image to video example

Directorial Camera Control

Take the director's chair with Seedance 1.5 Pro API's granular camera controls. Unlike standard generative models, Seedance allows you to script specific camera movements such as pans, tilts, zooms, and tracking shots. This precision enables the creation of structured, narrative-driven content.

Seedance 1.5 Pro API camera control showcase

Why creators choose Seedance 1.5 Pro API

Designed for professional content creation, Seedance 1.5 Pro API bridges the gap between AI experimentation and production-ready video workflows.

Unmatched Visual Realism

Seedance 1.5 Pro API utilizes a Decoupled Spatio-Temporal Diffusion Transformer architecture to achieve photorealistic lighting, physics-accurate motion, and intricate texture details at 1080p resolution.

Audio-Visual Unity

By generating audio and video simultaneously, Seedance 1.5 Pro API ensures that every visual event, from a footstep to an explosion, is perfectly matched by its corresponding sound.

Multi-Shot Consistency

Maintain character identity, lighting style, and environmental coherence across multiple generated clips, enabling the creation of longer, narrative-driven video projects.

How to Integrate Seedance 1.5 Pro API

Seamlessly integrate cinematic video generation into your app with Evolink's unified API.

1

Step 1 — Get Your API Key

Sign up on Evolink.ai and generate your secure API key from the dashboard. This key authenticates all your requests to the Seedance 1.5 Pro endpoint.

2

Step 2 — Submit Generation Task

Send a POST request to `/v1/video/generations` with your text prompt or image URL. The API processes this asynchronously and returns a `task_id` for tracking.

3

Step 3 — Retrieve Video Result

Use the `task_id` to poll the status endpoint or configure a webhook. Once completed, you'll receive a secure URL to download your synchronized audio-video file.

Seedance 1.5 Pro API Capabilities

Technical specifications for high-end video production

Audio

Native Audio Synthesis

Generates synchronized background music, sound effects, and dialogue tracks directly from text prompts.

Quality

1080p High Definition

Outputs broadcast-ready video at 1920x1080 resolution, ensuring crisp details on all screens.

Flexibility

Variable Duration

Supports variable video lengths from 4 to 12 seconds to fit different storytelling needs.

Intelligence

Advanced Prompt Adherence

Understanding complex prompts with high accuracy, ensuring every detail is represented.

Control

Cinematic Camera API

Full programmatic control over camera movement for automated video production pipelines.

Licensing

Commercial Rights

Commercial usage rights subject to BytePlus terms, enabled securely through the Evolink platform.

Seedance 1.5 Pro API vs. Competitors

Compare lead market models hosted on Evolink.

ModelDurationResolutionPriceStrength
Seedance 1.5 Pro API4–12s1080p$0.035 / secNative Audio Sync, Cinematic Camera Control, Developed by ByteDance Seed Team
Kling 1.6 Pro5s/10s1080p~$0.15 / secHigh realism, Professional Mode controls
Wan 2.6 (Alibaba)5s/10s/15s1080p~$0.08 / secStrong semantic understanding, smooth motion

Seedance 1.5 Pro API Frequently Asked Questions

Everything you need to know about the product and billing.

Seedance 1.5 Pro is the cutting-edge AI video generation model developed by the 'Seed' team at ByteDance. It represents a significant advancement in multimodal synthesis, featuring a unique Dual-Branch architecture that generates high-fidelity video and quality-synchronized audio simultaneously. It is designed for professional creators needing 1080p resolution and precise camera controls. Evolink integrates this powerful API to provide seamless access for developers and enterprises.
Seedance 1.5 Pro was researched and developed by the ByteDance Seed Team, a specialized AI research group focused on pushing the boundaries of generative media. Evolink serves as an API integration partner, making this sophisticated model accessible to a wider range of applications and workflows.
The model uses a joint audio-visual generation approach. Instead of post-processing audio, the video and audio streams are synthesized in parallel branches that communicate with each other. This allows the model to 'see' the action (like a car accelerating) and simultaneously 'speak' the corresponding sound (engine roaring), ensuring millisecond-level synchronization without manual editing.
Users can control camera movements such as Pan (horizontal), Tilt (vertical), Zoom, and Roll. These controls mimic real-world cinematography, allowing directors to plan shots precisely. You can define these movements via text prompts or specific API parameters to achieve the exact visual narrative required.
Yes, Seedance 1.5 Pro API supports Image-to-Video (I2V). You can upload a reference image as the initial frame, and the model will animate it based on your prompt while strictly adhering to the original image's character identity, lighting, and style.
Videos are typically output in MP4 format (H.264) at 1080p resolution (1920x1080 for 16:9, or 1080x1920 for 9:16). The standard frame rate is 24fps, providing a cinematic look compatible with professional editing timelines.
POST
/v1/videos/generations

Create Video

Seedance 1.5 Pro (seedance-1.5-pro) model supports multiple generation modes including text-to-video and image-to-video.

Asynchronous processing mode, use the returned task ID to .

Generated video links are valid for 24 hours, please save them promptly.

Request Parameters

modelstringRequiredDefault: seedance-1.5-pro

Video generation model name.

Exampleseedance-1.5-pro
promptstringRequired

Prompt describing what kind of video to generate.

Notes
  • Limited to 2000 tokens
ExampleA cat playing piano
image_urlsarrayOptional

Reference image URL list for image-to-video feature.

Notes
  • 1-2 images per request for image-to-video
  • Max size: 10MB per image
  • Formats: .jpg, .jpeg, .png, .webp
  • URLs must be directly viewable by the server
Examplehttp://example.com/image1.jpg
durationintegerOptionalDefault: 5

Specifies the duration of the generated video (in seconds).

ValueDescription
4-12Any integer value between 4 and 12 seconds
Notes
  • Billing is based on duration; longer durations result in higher costs
Example5
qualitystringOptionalDefault: 720p

Video resolution.

ValueDescription
480pLower resolution, 0.46x pricing
720pStandard definition, 1.0x pricing (default)
1080pHigh definition, 2.23x pricing
Example720p
aspect_ratiostringOptionalDefault: 16:9

Video aspect ratio.

ValueDescription
16:9Landscape video (default for text-to-video)
9:16Portrait video
1:1Square video
4:3Standard video
3:4Portrait standard
21:9Ultra-wide video
adaptiveAdaptive ratio (default for image-to-video)
Example'16:9'
generate_audiobooleanOptionalDefault: true

Whether to generate audio. Enabling will increase cost.

ValueDescription
trueVideo includes synchronized audio (voice, sound effects, background music)
falseVideo is silent
Notes
  • Place dialogue within double quotes in prompt to optimize audio generation
Exampletrue
callback_urlstringOptional

HTTPS callback address after task completion.

Notes
  • Triggered on completion, failure, or cancellation
  • Sent after billing confirmation
  • HTTPS only, no internal IPs
  • Max length: 2048 chars
  • Timeout: 10s, Max 3 retries
Examplehttps://your-domain.com/webhooks/video-task-completed

Request Example

{
  "model": "seedance-1.5-pro",
  "prompt": "A cat playing piano",
  "duration": 5,
  "quality": "720p",
  "aspect_ratio": "16:9",
  "generate_audio": true
}

Response Example

{
  "created": 1761313744,
  "id": "task-unified-1761313744-vux2jw0k",
  "model": "seedance-1.5-pro",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 165,
    "video_duration": 8
  },
  "type": "video",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 8,
    "user_group": "default"
  }
}