Seedance v1.5 Pro
Seedance v1.5 Pro is ByteDance's first audio-visual joint generation video model, released December 16, 2025. It produces synchronized dialogue, sound effects, and ambient audio alongside 1080p video in one generation pass, with multilingual voice and regional dialect support. Your use is subject to ByteDance's Terms & Privacy Policies.
View API reference- Price
- $0.01, Per secondLowest available configuration
import { experimental_generateVideo as generateVideo } from 'ai';
const result = await generateVideo({ model: 'bytedance/seedance-v1.5-pro', prompt: 'A serene mountain lake at sunrise.'});Copy link to headingPlayground
Try out Seedance v1.5 Pro by ByteDance. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Seedance v1.5 Pro
Your generated video will appear here.
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Getting started
Generate videos with Seedance v1.5 Pro using the experimental_generateVideo function from AI SDK 6 or later. AI Gateway handles routing and polls until the video is ready.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the video generation quickstart.
import { experimental_generateVideo as generateVideo } from 'ai';import fs from 'node:fs';import 'dotenv/config';
async function main() { const result = await generateVideo({ model: 'bytedance/seedance-v1.5-pro', prompt: 'A chicken flying into the sunset in the style of 90s anime', });
// Save the generated video fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
console.log('Video saved to output.mp4');}
main().catch(console.error);Top-level parameters
Exercise the supported top-level params: prompt, aspectRatio, resolution, and duration.
import { experimental_generateVideo as generateVideo } from 'ai';import fs from 'node:fs';import 'dotenv/config';
async function main() { const result = await generateVideo({ model: 'bytedance/seedance-v1.5-pro', prompt: 'A chicken flying into the sunset in the style of 90s anime', aspectRatio: '16:9', resolution: '1280x720', duration: 5, });
// Save the generated video fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
console.log('Video saved to output.mp4');}
main().catch(console.error);| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | No | Text description of the video to generate. |
duration | number | No | Video length in seconds. 4-12 seconds. |
resolution | string | No | Resolution ('854x480', '1280x720', '1920x1080'). |
aspectRatio | string | No | Aspect ratio ('16:9', '4:3', '1:1', '3:4', '9:16', '21:9'). |
generateAudio | boolean | No | Generate synchronized audio with the video. |
frameImages | Array<{ image: string; frameType: 'first_frame' | 'last_frame' }> | No | First and last frames of the clip. A first_frame entry replaces prompt.image and wins when both are set, and adding a last_frame transitions between the two. Seedance accepts image URLs only, so host local files on Vercel Blob first. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Image | jpeg, png, webp, bmp, tiff, gif, heic, heif | url | 2 | 30 MB | ≥300px · ≤6000px · aspect 2:5–5:2 |
Provider options (bytedance)
Load the compatible Seedance options under providerOptions.bytedance. Frames and references are passed at the top level through frameImages and inputReferences, which change the call shape and are shown in their own examples below.
import { experimental_generateVideo as generateVideo } from 'ai';import fs from 'node:fs';import 'dotenv/config';
async function main() { const result = await generateVideo({ model: 'bytedance/seedance-v1.5-pro', prompt: 'A chicken flying into the sunset in the style of 90s anime', resolution: '1280x720', duration: 5, providerOptions: { bytedance: { cameraFixed: true, serviceTier: 'default', watermark: false, returnLastFrame: true, pollIntervalMs: 5000, pollTimeoutMs: 600000, }, }, });
// Save the generated video fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
console.log('Video saved to output.mp4');}
main().catch(console.error);Pass these Seedance-specific options under providerOptions.bytedance in your generateVideo call.
| Parameter | Type | Required | Description |
|---|---|---|---|
lastFrameImage | string | No | URL of the last frame image, enabling first+last frame mode. Legacy alternative to the top-level frameImages, used only when frameImages is omitted. |
draft | boolean | No | Generate a 480p preview for fast iteration. Seedance v1.5 Pro only. |
watermark | boolean | No | Add a watermark to the video. |
cameraFixed | boolean | No | Fix the camera position during generation. |
returnLastFrame | boolean | No | Return the last frame of the generated video. Useful for chaining consecutive videos. |
serviceTier | 'default' | 'flex' | No | 'default' for online inference. 'flex' for offline at 50% cost, higher latency. |
pollIntervalMs | number | No | How often to check task status. Defaults to 3000. |
pollTimeoutMs | number | No | Maximum wait time. Defaults to 300000 (5 minutes). |
Frames take priority over references
Frames and references are mutually exclusive. When frameImages is set, inputReferences and the legacy providerOptions.bytedance.referenceImages / referenceVideos are dropped with a warning.
The top-level parameters win over their provider-option equivalents: frameImages overrides prompt.image and lastFrameImage, and inputReferences overrides referenceImages and referenceVideos. Set one or the other, not both.
providerOptions.bytedance.referenceAudio has no top-level equivalent, so it stays a provider option and is sent alongside whichever reference path you use.
Text-to-video with audio
Generate video with synchronized audio. Requires Seedance v1.5 Pro or a Seedance 2.0 series model.
import { experimental_generateVideo as generateVideo } from 'ai';import fs from 'node:fs';import 'dotenv/config';
async function main() { const result = await generateVideo({ model: 'bytedance/seedance-v1.5-pro', prompt: 'A thunderstorm rolling over a vast wheat field, lightning illuminating the clouds, rain beginning to fall', resolution: '1280x720', duration: 5, generateAudio: true, providerOptions: { bytedance: { pollTimeoutMs: 600000, }, }, });
// Save the generated video fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
console.log('Video saved to output.mp4');}
main().catch(console.error);First and last frame
Generate a video that transitions smoothly between a starting and ending image. Pass both frames through the top-level frameImages, tagging one first_frame and one last_frame. Seedance requires image URLs, so host local images on Vercel Blob first.
import { experimental_generateVideo as generateVideo } from 'ai';import fs from 'node:fs';import 'dotenv/config';
async function main() { const result = await generateVideo({ model: 'bytedance/seedance-v1.5-pro', prompt: 'Create a 360-degree orbiting camera shot based on this photo', frameImages: [ { image: 'https://example.com/first-frame.jpg', frameType: 'first_frame', }, { image: 'https://example.com/last-frame.jpg', frameType: 'last_frame' }, ], duration: 5, providerOptions: { bytedance: { watermark: false, pollTimeoutMs: 600000, }, }, });
// Save the generated video fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
console.log('Video saved to output.mp4');}
main().catch(console.error);Copy link to headingMore models by ByteDance
| Model |
|---|
| — | $0.003/M | $0.04/img | — | | 07/11/2026 | |||||||||
| 262K | 1.9 s | 106 tps | $0.50/M | $2.50/M | Read$0.10/M | — | | 06/23/2026 | ||||||
| — | $0.04/img | — | | 02/13/2026 | ||||||||||
| — | $0.04/img | — | | 12/03/2025 | ||||||||||
| — | $0.03/img | — | | 09/09/2025 | ||||||||||
| 256K | 1.0 s | 106 tps | $0.25/M+1 more | $2/M+1 more | Read$0.05/M | — | | 09/01/2025 |
Copy link to headingAbout Seedance v1.5 Pro
Seedance v1.5 Pro shifts the Seedance line from visual generation alone to joint audio-visual creation. Released December 16, 2025, it's the first Seedance model to generate voice, sound effects, and ambient audio synchronized to video in a single inference pass. You don't run a separate text-to-speech or audio compositing step.
The audio system supports multilingual speech generation across six languages: Chinese, English, Japanese, Korean, Spanish, and Indonesian. It also covers regional dialects such as Sichuanese and Cantonese. Vocal synthesis targets prosody and intonation that track the scene. Spatial reverb in sound effects matches the visual scene's physical context. ByteDance's release cites lip movement alignment, intonation patterning, and performance rhythm synchronization as focus areas versus listed baselines. See https://console.byteplus.com/ark/region:ark+ap-southeast-1/model/detail?Id=seedance-1-5-pro for tables and comparisons.
On the video side, Seedance v1.5 Pro raises the ceiling relative to Seedance 1.0 Pro. Where 1.0 focused on motion stability, 1.5 Pro extends camera control and finishing. You get cinematic camera controls including continuous long takes and dolly zooms, color grading controls, more facial detail in close-ups, and richer dynamic motion. Output supports 480p, 720p, and 1080p resolution at 24 fps, with clips from four to 12 seconds and seven aspect ratios.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: For audio-visual workflows, confirm that your integration layer handles the combined audio-video output format before you deploy to production. Compare rates (N/A; N/A).
- Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Seedance v1.5 Pro
Best for
- Character-driven video content: Creative briefs that include synchronized dialogue, lip alignment, and vocal performance
- Multilingual content production: Chinese, English, Japanese, Korean, Spanish, or Indonesian voice plus regional dialect variants
- Cinematic short-form content: Dolly zooms, long takes, and color grading that go beyond typical social clip defaults
- Ambient-audio storytelling: Product demos, branded content, and explainer videos where spatial sound effects match the scene without manual audio post-production
Consider alternatives when
- Visual-only pipelines: Seedance 1.0 Pro offers lower cost when audio isn't a requirement
- Maximum speed and cost efficiency: Seedance 1.0 Pro Fast is the primary choice when those drivers dominate
- Unsupported languages: Verify support before committing when you need a dialect or language not yet covered by the audio system
Copy link to headingConclusion
Seedance v1.5 Pro closes the gap between AI video generation and full audio-visual production by eliminating the post-processing step of adding synchronized audio. For any project where voice, sound design, and video must arrive together, it's the only Seedance model that handles all three in one pass.
Copy link to headingFrequently Asked Questions
What languages does Seedance v1.5 Pro support for voice generation?
Six languages: Chinese, English, Japanese, Korean, Spanish, and Indonesian. Regional dialect coverage includes Sichuanese and Cantonese.
Does Seedance v1.5 Pro require a separate text-to-speech step for audio?
No. Seedance v1.5 Pro generates voice, ambient sound, and sound effects in the same inference pass as the video. You don't need an external audio pipeline.
How does audio-visual synchronization work in Seedance v1.5 Pro?
Seedance v1.5 Pro trains to align lip movements, intonation patterns, and performance rhythm with visual content. ByteDance's release documentation reports lower audio-visual misalignment than listed baselines in its tables. See https://console.byteplus.com/ark/region:ark+ap-southeast-1/model/detail?Id=seedance-1-5-pro.
What video specifications does Seedance v1.5 Pro support?
Resolutions of 480p, 720p, and 1080p at 24 fps, clip durations from four to 12 seconds, and seven aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, and 9:21.
How does Seedance v1.5 Pro differ from Seedance 1.0 Pro on video quality alone?
Seedance 1.5 Pro adds cinematic camera techniques (dolly zooms, long takes), color grading controls, and more facial detail in close-ups, beyond the motion stability focus of 1.0 Pro.
Can Seedance v1.5 Pro generate ambient sound without spoken dialogue?
Yes. The audio system generates spatial sound effects and ambient audio that match the visual scene's physical environment, whether or not the scene contains speech.