Saltar al contenido principal
POST
/
video
/
queue
/api/v1/video/queue
curl --request POST \
  --url https://api.venice.ai/api/v1/video/queue \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "seedance-2-0-text-to-video",
  "prompt": "Commerce being conducted in the city of Venice, Italy.",
  "duration": "10s",
  "consents": {},
  "negative_prompt": "low resolution, error, worst quality, low quality, defects",
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "upscale_factor": 2,
  "audio": true,
  "image_url": "data:image/png;base64,iVBORw0K...",
  "end_image_url": "data:image/png;base64,iVBORw0K...",
  "audio_url": "data:audio/mpeg;base64,SUQzBAA...",
  "video_url": "data:video/mp4;base64,AAAAFGZ0eXA...",
  "reference_image_urls": [
    "data:image/png;base64,iVBORw0K..."
  ],
  "reference_video_urls": [
    "https://example.com/reference-clip.mp4"
  ],
  "reference_audio_urls": [
    "data:audio/mpeg;base64,SUQzBAAAAAA..."
  ],
  "elements": [
    {
      "frontal_image_url": "data:image/png;base64,iVBORw0K...",
      "reference_image_urls": [
        "data:image/png;base64,iVBORw0K..."
      ]
    }
  ],
  "scene_image_urls": [
    "data:image/png;base64,iVBORw0K..."
  ]
}
'
{
  "model": "video-model-123",
  "queue_id": "123e4567-e89b-12d3-a456-426614174000",
  "download_url": "<string>"
}
Llama a /video/quote para obtener una estimación de precio y, a continuación, consulta /video/retrieve con el queue_id devuelto hasta que se complete. Los modelos privados también devuelven un download_url para el vídeo terminado. Es una URL de entrega de corta duración (algunos reintentos están bien si una descarga se interrumpe); consulta la guía de generación de vídeo para conocer los detalles y el DELETE opcional para privacidad.

​
Seedance 2.0

Para los modelos seedance-2-0-* (text-to-video, image-to-video, reference-to-video, además de las variantes -fast-*), consulta la Guía de Seedance 2.0 para el modelo de cuatro flujos de trabajo (Reference / Edit / Extend / Stitch), patrones canónicos de prompt, límites de entrada multimodal y detalles de precios.

​
Consentimiento de Seedance

Cuando una solicitud de image- o reference-to-video de Seedance contiene un rostro humano, la API devuelve un 409 needs_consent con el texto de la política, y debes reenviar la misma solicitud con una atestación consents.seedance. Consulta la Guía de consentimiento para contenido de rostro de Seedance para conocer el flujo completo, el objeto de consentimiento, deduplicación y revocación.

​
Escalado de vídeo

Para el modelo topaz-video-upscale, usa upscale_factor (1, 2 o 4) en lugar de resolution y proporciona un video_url. La duración y los FPS se detectan automáticamente del archivo de vídeo. Consulta la Guía de escalado de vídeo para detalles completos y ejemplos.

Autorizaciones

​
Authorization
string
header
requerido

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Cuerpo

application/json

Request body for video generation. Available fields and valid values vary by model.

​
model
string
requerido

The model to use for video generation.

Ejemplo:

"seedance-2-0-text-to-video"

​
prompt
string
requerido

The prompt to use for video generation. Required for most models. The maximum length varies by model (default 2500 characters, up to 10000 for some models such as Seedance 2.0).

Required string length: 1 - 10000
Ejemplo:

"Commerce being conducted in the city of Venice, Italy."

​
duration
enum<string>
requerido

The duration of the video to generate. Available options vary by model.

Opciones disponibles:
2s,
3s,
4s,
5s,
6s,
7s,
8s,
9s,
10s,
11s,
12s,
13s,
14s,
15s,
16s,
18s,
20s,
25s,
30s,
1 gen,
Auto
Ejemplo:

"10s"

​
consents
object

Optional provider-specific consent attestations. Seedance consent is required only when submitted media contains faces.

​
negative_prompt
string

Optional negative prompt. The maximum length varies by model (default 2500 characters, up to 10000 for some models).

Maximum string length: 10000
Ejemplo:

"low resolution, error, worst quality, low quality, defects"

​
aspect_ratio
enum<string>

The aspect ratio of the video. Available options vary by model. Some models do not support aspect_ratio.

Opciones disponibles:
1:1,
2:3,
3:2,
3:4,
4:3,
9:16,
16:9,
21:9
Ejemplo:

"16:9"

​
resolution
enum<string>

The resolution of the video. Available options vary by model. Some models do not support resolution. Use upscale_factor for upscale models.

Opciones disponibles:
256p,
360p,
480p,
540p,
580p,
720p,
1080p,
1440p,
2160p,
4k,
2x,
4x,
true_1080p
Ejemplo:

"720p"

​
upscale_factor
enum<integer>
predeterminado:2

For upscale models only. 1 = quality enhancement, 2 = double resolution (default), 4 = quadruple.

Opciones disponibles:
1,
2,
4
Ejemplo:

2

​
audio
boolean
predeterminado:true

For models which support audio generation and configuration. Defaults to true.

Ejemplo:

true

​
image_url
string

For image-to-video models, the reference image. Must be a URL (http/https) or a data URL (data:image/...).

Ejemplo:

"data:image/png;base64,iVBORw0K..."

​
end_image_url
string

For models that support end images or transitions, the end frame image. Must be a URL or data URL.

Ejemplo:

"data:image/png;base64,iVBORw0K..."

​
audio_url
string

For models that support audio input, background music. Must be a URL or data URL. Supported: WAV, MP3. Max: 30s, 15MB.

Ejemplo:

"data:audio/mpeg;base64,SUQzBAA..."

​
video_url
string

For models that support video input (video-to-video, upscale). Must be a URL or data URL. Supported: MP4, MOV, WebM.

Ejemplo:

"data:video/mp4;base64,AAAAFGZ0eXA..."

​
reference_image_urls
string[]

For models with reference image support, up to 9 images for character/style consistency. Each must be a URL or data URL.

Maximum array length: 9
Ejemplo:
["data:image/png;base64,iVBORw0K..."]
​
reference_video_urls
string[]

For models with reference video support (e.g. Seedance 2.0 R2V), up to 3 reference video URLs (role: "reference_video") used to inherit subject motion, camera movement, and overall style. Per-clip 2–15 s, .mp4 or .mov, ≤50 MB; aggregate duration ≤15 s. Each must be a URL or data URL.

Maximum array length: 3
Ejemplo:
["https://example.com/reference-clip.mp4"]
​
reference_audio_urls
string[]

For models with reference audio support (e.g. Seedance 2.0 R2V), up to 3 reference audio URLs (role: "reference_audio") used as donors for vocal timbre, narration, or sound effects. Per-clip 2–15 s, .wav or .mp3; aggregate duration ≤15 s. Must be paired with at least one reference image or reference video — audio-only Reference workflows are rejected at validation. Each must be a URL or data URL.

Maximum array length: 3
Ejemplo:
["data:audio/mpeg;base64,SUQzBAAAAAA..."]
​
elements
object[]

For models with advanced element support (e.g., Kling O3 R2V). Up to 4 elements defining characters/objects. Reference in prompt as @Element1, @Element2, etc.

Maximum array length: 4
Ejemplo:
[
  {
    "frontal_image_url": "data:image/png;base64,iVBORw0K...",
    "reference_image_urls": ["data:image/png;base64,iVBORw0K..."]
  }
]
​
scene_image_urls
string[]

For models with advanced element support. Up to 4 scene reference images. Reference in prompt as @Image1, @Image2, etc.

Maximum array length: 4
Ejemplo:
["data:image/png;base64,iVBORw0K..."]

Respuesta

Video generation request queued successfully

​
model
string
requerido

The ID of the model used for video generation.

Ejemplo:

"video-model-123"

​
queue_id
string
requerido

The ID of the video generation request.

Ejemplo:

"123e4567-e89b-12d3-a456-426614174000"

​
download_url
string

Pre-signed URL to download the completed video. Only present for VPS-backed models. When provided, the retrieve endpoint returns JSON status only (no video stream). Fetch this URL after status is COMPLETED to get the video/mp4 file. Valid for 24 hours.