bytedance/seedance/1.5/pro/text-to-video
ByteDance Seedance v1.5 Pro text-to-video model generating cinematic video from text prompts with native audio generation, camera control, and professional-grade output quality.
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runbytedance/seedance/1.5/pro/text-to-videoInput Schema
7 parameters · 1 required · 6 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | The text prompt to generate a video from. · Min length: 3 · Max length: 50000 · Default: "Photorealistic style: Under a clear blue sky, a vast expanse of white daisy fields stretches out. The camera gradually zooms in and finally fixates on a close-up of a single daisy, with several glistening dewdrops resting on its petals." |
seed | integer | Optional | Random seed for reproducible results. Set to -1 for random seed. |
duration | integer | Optional | Duration of the video in seconds. · Options: 4, 5, 6, 7, 8, 9, 10, 11, 12 · Default: 5 456789101112 |
resolution | string | Optional | The resolution of the video to generate. · Options: 480p, 720p, 1080p · Default: "720p" 480p720p1080p |
aspect_ratio | string | Optional | The aspect ratio of the generated video. · Options: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 · Default: "16:9" 21:916:94:31:13:49:16 |
camera_fixed | boolean | Optional | Whether to fix the camera position. · Default: false |
generate_audio | boolean | Optional | Whether to generate audio for the video. · Default: true |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "bytedance/seedance/1.5/pro/text-to-video",
"prompt": "Photorealistic style: Under a clear blue sky, a vast expanse of white daisy fields stretches out. The camera gradually zooms in and finally fixates on a close-up of a single daisy, with several glistening dewdrops resting on its petals.",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"camera_fixed": false,
"generate_audio": true
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Bytedance Seedance 1.5 Pro Text To Video
Bytedance Seedance 1.5 Pro Text To Video is built for text-led cinematic generation with optional audio integrated into the resulting scene. It gives creative and production teams a focused way to move from an approved brief or source asset to a reviewable result without fragmenting the job across unrelated tools. The model is most valuable when visual intent, brand suitability, and downstream usability all matter, because its output can enter an editorial, campaign, product, or content pipeline as a purposeful asset rather than an isolated experiment.
In practice, teams can use Bytedance Seedance 1.5 Pro Text To Video during a structured cycle of briefing, generation, comparison, and refinement. Establish the subject, audience, visual objective, and acceptance criteria first; prepare any reference media at suitable quality; then evaluate alternatives for composition, continuity, realism, and communication value before delivery. This workflow keeps creative judgment central while making repeated production easier to review, reproduce, and scale for the specific bytedance/seedance/1.5/pro/text-to-video task.
Highlights
Joint audio-visual creation. Joint audio-visual creation gives bytedance › seedance › 1.5 › pro › text to video a recognizable technical advantage: reviewers can assess this property directly in the generated asset instead of inferring it from request mechanics.
Complex prompt choreography. bytedance › seedance › 1.5 › pro › text to video applies complex prompt choreography to the visual or temporal result itself, helping artists make a meaningful quality decision during selection and refinement.
Cinematic camera language. For bytedance › seedance › 1.5 › pro › text to video, cinematic camera language supports coherent assets across the intended creative workflow and distinguishes this capability from a simple format or delivery option.
Strong temporal consistency. The practical value of strong temporal consistency is visible in the finished media from bytedance › seedance › 1.5 › pro › text to video, where it supports repeatable art direction rather than merely exposing another request setting.
Pricing
| Duration | Resolution | Audio | Price |
|---|---|---|---|
| 4s | 480p | Off | $0.048000 |
| 4s | 480p | On | $0.096000 |
| 4s | 720p | Off | $0.104000 |
| 4s | 720p | On | $0.208000 |
| 4s | 1080p | Off | $0.240000 |
| 4s | 1080p | On | $0.480000 |
| 5s | 480p | Off | $0.060000 |
| 5s | 480p | On | $0.120000 |
| 5s | 720p | Off | $0.130000 |
| 5s | 720p | On | $0.260000 |
| 5s | 1080p | Off | $0.300000 |
| 5s | 1080p | On | $0.600000 |
| 6s | 480p | Off | $0.072000 |
| 6s | 480p | On | $0.144000 |
| 6s | 720p | Off | $0.156000 |
| 6s | 720p | On | $0.312000 |
| 6s | 1080p | Off | $0.360000 |
| 6s | 1080p | On | $0.720000 |
| 7s | 480p | Off | $0.084000 |
| 7s | 480p | On | $0.168000 |
| 7s | 720p | Off | $0.182000 |
| 7s | 720p | On | $0.364000 |
| 7s | 1080p | Off | $0.420000 |
| 7s | 1080p | On | $0.840000 |
| 8s | 480p | Off | $0.096000 |
| 8s | 480p | On | $0.192000 |
| 8s | 720p | Off | $0.208000 |
| 8s | 720p | On | $0.416000 |
| 8s | 1080p | Off | $0.480000 |
| 8s | 1080p | On | $0.960000 |
| 9s | 480p | Off | $0.108000 |
| 9s | 480p | On | $0.216000 |
| 9s | 720p | Off | $0.234000 |
| 9s | 720p | On | $0.468000 |
| 9s | 1080p | Off | $0.540000 |
| 9s | 1080p | On | $1.080000 |
| 10s | 480p | Off | $0.120000 |
| 10s | 480p | On | $0.240000 |
| 10s | 720p | Off | $0.260000 |
| 10s | 720p | On | $0.520000 |
| 10s | 1080p | Off | $0.600000 |
| 10s | 1080p | On | $1.200000 |
| 11s | 480p | Off | $0.132000 |
| 11s | 480p | On | $0.264000 |
| 11s | 720p | Off | $0.286000 |
| 11s | 720p | On | $0.572000 |
| 11s | 1080p | Off | $0.660000 |
| 11s | 1080p | On | $1.320000 |
| 12s | 480p | Off | $0.144000 |
| 12s | 480p | On | $0.288000 |
| 12s | 720p | Off | $0.312000 |
| 12s | 720p | On | $0.624000 |
| 12s | 1080p | Off | $0.720000 |
| 12s | 1080p | On | $1.440000 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| Use it when text-led cinematic generation with optional audio integrated into the resulting scene is the central production goal | Choose a different model when the required media task is fundamentally different |
| The team needs several reviewable creative alternatives | Exact deterministic reproduction is mandatory |
| Visual quality and practical downstream use both matter | Editable source layers or native project files are required |
| A managed generation step fits the delivery workflow | A live frame-by-frame interactive editor is essential |
| The documented inputs cover the available source assets | Required source media or controls fall outside the documented fields |
Prompt Guide
State the intended result first, then describe the subject, environment, action, visual treatment, and delivery constraints. Keep instructions concrete, avoid conflicting directions, and change one creative variable at a time when comparing outputs. For source-driven work, describe what should remain recognizable as clearly as what should change.
{
"prompt": "Photorealistic style: Under a clear blue sky, a vast expanse of white daisy fields stretches out. The camera gradually zooms in and finally fixates on a close-up of a single daisy, with several glistening dewdrops resting on its petals.",
"duration": 5,
"resolution": "720p",
"generate_audio": true
}
Technical Specs
| Property | Details |
|---|---|
seed | Type / options: integer<br>Required: No<br>Description: Random seed for reproducible results. Set to -1 for random seed. |
prompt | Type / options: string<br>Required: Yes<br>Description: The text prompt to generate a video from. |
duration | Type / options: integer · 4 / 5 / 6 / 7 / 8 / 9 / 10 / 11 / 12<br>Required: No<br>Description: Duration of the video in seconds. |
resolution | Type / options: string · 480p / 720p / 1080p<br>Required: No<br>Description: The resolution of the video to generate. |
aspect_ratio | Type / options: string · 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16<br>Required: No<br>Description: The aspect ratio of the generated video. |
camera_fixed | Type / options: boolean<br>Required: No<br>Description: Whether to fix the camera position. |
generate_audio | Type / options: boolean<br>Required: No<br>Description: Whether to generate audio for the video. |
Related Models
bytedance/dreamactor/2.0bytedance/lynxbytedance/omnihuman/1.0

