> ## Documentation Index
> Fetch the complete documentation index at: https://tryunsora.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Create video
> Queue a video generation job with any supported model and poll until complete.
Creates a video generation with any supported video model. Credits are charged when the job is queued. Poll [Poll video status](/api-reference/video/poll-status) with `generation.id` until `status` is `COMPLETED` or `FAILED`.
## Supported models
Pass the model key in the `model` body field. Default: `seedance-2.0`.
| Model key | Name | Duration | Aspect ratios | Sound |
| ------------------- | ------------------------ | -------------------- | ------------------------------------------- | --------------- |
| `kling-standard` | Kling v3.0 Standard | 1–15s | `16:9`, `1:1`, `9:16` | ✅ `sound` |
| `kling-pro` | Kling v3.0 Pro | 3–15s | `16:9`, `1:1`, `9:16` | ✅ `sound` |
| `veo` | Google Veo 3.1 | 4, 6, or 8s | `16:9`, `9:16` | ✅ `sound` |
| `veo-fast` | Google Veo 3.1 Fast | 4, 6, or 8s | `16:9`, `9:16` | ✅ `sound` |
| `veo-lite` | Google Veo 3.1 Lite | 4, 6, or 8s | `16:9`, `9:16` | ✅ `sound` |
| `sora-2` | OpenAI Sora 2 | 4, 8, 12, 16, or 20s | `16:9`, `9:16` | — |
| `sora-2-pro` | OpenAI Sora 2 Pro | 4, 8, 12, 16, or 20s | `16:9`, `9:16` | — |
| `wan` | Alibaba Wan 2.6 | 5–15s | `16:9`, `9:16` | — |
| `seedance-2.0` | Seedance 2.0 (1080p) | 4–15s | `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | `generateAudio` |
| `seedance-2.0-fast` | Seedance 2.0 Fast (720p) | 4–15s | `21:9`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16` | `generateAudio` |
All models run on WaveSpeed and share the same form inputs: `image` / `lastImage` for start/end frames, `referenceImages` (plus `referenceVideos` / `referenceAudios` on Seedance) for reference-guided generation, `negativePrompt`, `sound` / `generateAudio`, and `resolution` (Veo / Wan).
## Headers
| Header | Required | Description |
| ----------------- | -------- | -------------------------------------------------------------------- |
| `Authorization` | Yes | `Bearer uns_live_*` API key or Clerk JWT |
| `Idempotency-Key` | No | Max 128 chars. Replays the same response for 24h on API key requests |
| `Content-Type` | Yes | `application/json` |
## Request body
Text prompt describing the video to generate.
Video model key from the table above. Default: `seedance-2.0`.
Length in seconds (integer). Default: `5`. The valid range depends on the model (see table above).
Aspect ratio. Default: `16:9`. Valid values depend on the model (see table above).
What to avoid in the video. Supported by Kling, Veo, and Wan models.
Generate audio with the video. Default: `false`. Supported by Kling v3 and Veo 3.1 models — increases credit cost.
`720p` or `1080p` for Veo 3.1 and Wan 2.6 models. Seedance resolution is fixed by the model variant.
Start image URL for image-to-video. On Seedance models this switches to first/last-frame mode.
End/last image URL, for models that support start/end frames.
Reference image URLs. Veo 3.1 reference mode; Seedance omni reference (up to 9 public image URLs).
**Seedance only** — up to 3 public video URLs. Using video references increases credit cost.
**Seedance only** — up to 3 public audio URLs.
**Seedance only** — generate a soundtrack/audio for the video. Default: `false`.
## Credits
| Model | Pricing |
| ------------------- | --------------------------------------------------------------------- |
| `kling-standard` | 5s: 20 · 10s: 35 · 15s: 50 — with `sound`: 25 / 50 / 75 |
| `kling-pro` | 5s: 45 · 10s: 85 · 15s: 125 — with `sound`: 65 / 125 / 190 |
| `veo` | 9 credits/second — with `sound`: 18 credits/second |
| `veo-fast` | 4.5 credits/second — with `sound`: 6.75 credits/second (rounded up) |
| `veo-lite` | 3.6 credits/second (rounded up) |
| `sora-2` | 4s: 20 · 8s: 35 · 12s: 50 · 16s: 65 · 20s: 80 |
| `sora-2-pro` | 4s: 50 · 8s: 95 · 12s: 145 · 16s: 190 · 20s: 240 |
| `wan` | 720p — 5s: 20 · 10s: 40 · 15s: 60; 1080p — 5s: 30 · 10s: 60 · 15s: 90 |
| `seedance-2.0` | 5s: 40 · 10s: 80 · 15s: 100 — with `referenceVideos`: 80 / 140 / 200 |
| `seedance-2.0-fast` | 5s: 20 · 10s: 40 · 15s: 60 — with `referenceVideos`: 40 / 80 / 100 |
## Async completion
Poll `GET /video/status/{id}` — see [Poll video status](/api-reference/video/poll-status). No webhooks.
## Response
```json theme={null}
{
"success": true,
"generation": {
"id": "cm123abc",
"status": "QUEUED"
},
"model": "seedance-2.0",
"creditsDeducted": 40,
"creditsRemaining": 60
}
```
## Examples
```bash Text-to-video (Seedance) theme={null} theme={null}
curl -X POST "https://mvp.tryunsora.com/api/v1/videos/create" \
-H "Authorization: Bearer uns_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Slow cinematic drone shot over misty mountains at sunrise",
"aspectRatio": "16:9",
"duration": 5
}'
```
```bash Veo 3.1 with sound theme={null} theme={null}
curl -X POST "https://mvp.tryunsora.com/api/v1/videos/create" \
-H "Authorization: Bearer uns_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "veo",
"prompt": "A barista pours latte art in a cozy cafe, ambient chatter",
"aspectRatio": "16:9",
"duration": 8,
"sound": true
}'
```
```bash Kling Pro image-to-video theme={null} theme={null}
curl -X POST "https://mvp.tryunsora.com/api/v1/videos/create" \
-H "Authorization: Bearer uns_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kling-pro",
"prompt": "The character turns and smiles at the camera",
"image": "https://cdn.example.com/start.jpg",
"duration": 5
}'
```
```bash Sora 2 theme={null} theme={null}
curl -X POST "https://mvp.tryunsora.com/api/v1/videos/create" \
-H "Authorization: Bearer uns_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "sora-2",
"prompt": "A golden retriever surfs a small wave at sunset, slow motion",
"duration": 8
}'
```
```bash Seedance omni reference theme={null} theme={null}
curl -X POST "https://mvp.tryunsora.com/api/v1/videos/create" \
-H "Authorization: Bearer uns_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.0",
"prompt": "Character walks through neon alley, same outfit as reference",
"aspectRatio": "9:16",
"duration": 10,
"referenceImages": ["https://cdn.example.com/ref.jpg"]
}'
```
```bash Seedance first/last frame theme={null} theme={null}
curl -X POST "https://mvp.tryunsora.com/api/v1/videos/create" \
-H "Authorization: Bearer uns_live_YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.0",
"prompt": "Smooth transition from day to night over the city skyline",
"aspectRatio": "16:9",
"duration": 5,
"image": "https://cdn.example.com/frame-start.jpg",
"lastImage": "https://cdn.example.com/frame-end.jpg"
}'
```
## Errors
| HTTP | When |
| ----- | ---------------------------------------------------------------- |
| `400` | Invalid model, prompt, mode, ratio, duration, or reference files |
| `401` | Invalid auth |
| `402` | Insufficient credits |
| `404` | User not found |
| `429` | Rate limit exceeded |
| `500` | Server error |
## OpenAPI
````yaml POST /videos/create
openapi: 3.1.0
info:
title: Unsora API
version: 1.2.0
description: >-
Public API for Unsora integrations. Authenticate with Clerk JWT or
uns_live_* API key. API keys are rate-limited to 60 requests/minute and
support idempotency keys. Async jobs complete via polling GET
/image/status/{id}.
servers:
- url: https://mvp.tryunsora.com/api/v1
description: Versioned API (recommended)
security: []
tags:
- name: Clippings
- name: Connect
- name: Image Generations
- name: Music Generations
- name: Influencer Studio
- name: Posts
- name: Thumbnails
- name: User
- name: Video Generations
paths:
/videos/create:
post:
tags:
- Video Generations
summary: Create video generation
description: >-
Queue a video generation with any supported video model (Kling v3, Veo
3.1, Sora 2, Wan 2.6, Seedance 2.0).
parameters:
- name: Idempotency-Key
in: header
required: false
schema:
type: string
maxLength: 128
description: >-
Optional. Replays the original response for 24h when using an API
key.
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/CreateVideoRequest'
responses:
'200':
description: Job queued
content:
application/json:
schema:
$ref: '#/components/schemas/CreateVideoResponse'
'400':
description: Validation error
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'402':
description: Insufficient credits
content:
application/json:
schema:
$ref: '#/components/schemas/ErrorResponse'
'429':
description: Rate limit exceeded
security:
- bearerAuth: []
components:
schemas:
CreateVideoRequest:
type: object
description: >-
Create a video generation. `model` selects the video model. Use
image/lastImage for start/end frames, referenceImages (plus
referenceVideos/referenceAudios on Seedance) for reference-guided
generation.
properties:
prompt:
type: string
model:
type: string
default: seedance-2.0
enum:
- kling-standard
- kling-pro
- veo
- veo-fast
- veo-lite
- sora-2
- sora-2-pro
- wan
- seedance-2.0
- seedance-2.0-fast
description: >-
Video model to generate with. See the model table in the docs for
durations, ratios and features.
duration:
type: integer
default: 5
description: >-
Video length in seconds. Valid range depends on the model: Kling
Standard 1-15, Kling Pro 3-15, Veo 3.1 (all) 4-8, Sora 2 / Sora 2
Pro 4-20, Wan 2.6 5-15, Seedance 2.0 (both) 4-15.
aspectRatio:
type: string
default: '16:9'
description: >-
Aspect ratio. Kling: 16:9, 1:1, 9:16. Veo: 16:9, 9:16. Seedance:
21:9, 16:9, 4:3, 1:1, 3:4, 9:16.
negativePrompt:
type: string
description: What to avoid in the video. Supported by Kling, Veo and Wan models.
resolution:
type: string
description: >-
Output resolution (720p or 1080p) for Wan 2.6. Seedance output
resolution is fixed (2.0: 1080p, 2.0 Fast: 720p).
sound:
type: boolean
default: false
description: >-
Generate audio. Supported by Kling v3 and Veo 3.1 models (increases
credit cost).
image:
type: string
format: uri
description: >-
Start image URL for image-to-video. On Seedance models this switches
to first/last-frame mode.
lastImage:
type: string
format: uri
description: End/last image URL, for models that support start/end frames.
referenceImages:
type: array
items:
type: string
format: uri
description: >-
Reference image URLs. Veo 3.1 reference mode; Seedance omni
reference (up to 9).
referenceVideos:
type: array
items:
type: string
format: uri
maxItems: 3
description: >-
Seedance omni reference only — up to 3 video URLs. Using video
references increases credit cost.
referenceAudios:
type: array
items:
type: string
format: uri
maxItems: 3
description: Seedance omni reference only — up to 3 audio URLs.
generateAudio:
type: boolean
default: false
description: Seedance only — generate a soundtrack/audio for the video.
required:
- prompt
CreateVideoResponse:
type: object
properties:
success:
type: boolean
generation:
type: object
properties:
id:
type: string
status:
type: string
enum:
- QUEUED
- PROCESSING
- COMPLETED
- FAILED
required:
- id
- status
model:
type: string
enum:
- seedance_2.0
creditsDeducted:
type: number
creditsRemaining:
type: number
required:
- success
- generation
- model
ErrorResponse:
type: object
properties:
success:
type: boolean
error:
type: string
code:
type: string
message:
type: string
required:
- error
securitySchemes:
bearerAuth:
type: http
scheme: bearer
description: Clerk session JWT or Unsora API key (uns_live_*)
````