Mettre en file d'attente une génération vidéo

Queue a new video generation request.

Authentication: This endpoint accepts either a Bearer API key or a SIGN-IN-WITH-X header for x402 wallet-based authentication. The legacy X-Sign-In-With-X header is also accepted during migration. When using x402, a 402 Payment Required response indicates insufficient balance and includes top-up instructions.

POST /video/queue

/api/v1/video/queue

cURL

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-basic",
  "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",
  "omni_reference_task_type": "edit",
  "resolution": "720p",
  "upscale_factor": 2,
  "enhancement_model": "Proteus",
  "target_fps": 60,
  "softness": 3,
  "creativity": 0.5,
  "realism": 0.5,
  "sharp": 0.5,
  "compression": 0.5,
  "noise": 0.5,
  "halo": 0.5,
  "grain": 0,
  "recover_detail": 0.5,
  "h264_output": false,
  "output_format": "mp4",
  "slowdown_factor": 1,
  "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..."
  ],
  "reference_document_urls": [
    "https://example.com/brief.pdf"
  ],
  "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..."
  ],
  "keyframes": [
    {
      "image_url": "data:image/png;base64,iVBORw0K...",
      "frame_index": 0
    },
    {
      "image_url": "data:image/png;base64,iVBORw0K...",
      "frame_index": 120
    }
  ]
}
'

200

{
  "model": "video-model-123",
  "queue_id": "123e4567-e89b-12d3-a456-426614174000",
  "download_url": "<string>"
}

Appelez /video/quote pour obtenir une estimation du prix, puis interrogez /video/retrieve avec le queue_id renvoyé jusqu’à ce que la génération soit terminée.

Les modèles privés renvoient également un download_url pour la vidéo terminée. Il s’agit d’une URL de livraison à durée de vie courte (quelques relances sont acceptables si un téléchargement échoue) ; voir le guide de génération vidéo pour les détails et la méthode DELETE optionnelle pour la confidentialité.

​

Seedance 2.0 & 2.5

Pour les modèles seedance-2-0-*-basic et seedance-2-5-*-basic (text-to-video, image-to-video, reference-to-video, plus les variantes -fast-* de Seedance 2.0), voir le guide Seedance 2.0 & 2.5 pour le modèle à quatre workflows (Reference / Edit / Extend / Stitch), les valeurs aspect_ratio / duration alignées sur la source, les limites multimodales spécifiques à chaque famille, la politique média de l’API publique et les détails de tarification.

​

Politique média publique de Seedance

Les modèles Seedance publics n’utilisent pas d’attestation de consentement (consents.seedance / needs_consent). Les médias contenant des personnes détectables peuvent être rejetés en amont. Utilisez l’application Venice ou Studio pour bénéficier de l’ensemble complet des fonctionnalités Seedance. Voir le guide Seedance pour plus de détails.

​

Agrandissement vidéo

Pour le modèle topaz-video-upscale, utilisez upscale_factor (1, 2 ou 4) au lieu de resolution, et fournissez un video_url. La durée et le FPS sont détectés automatiquement à partir du fichier vidéo. Voir le guide d’agrandissement vidéo pour les détails complets et les exemples.

---

Autorisations

BearerAuthsiwx

Authorization · string · header · requis

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

Corps

application/json

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

model · string · requis

The model to use for video generation.

Exemple:

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

prompt · string · requis

The prompt to use for video generation. Required for most models. The maximum length varies by model (default 2500 characters, up to 20000 for some models).

Required string length: 1 - 20000

Exemple:

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

duration · enum<string> · requis

The duration of the video to generate. Available options vary by model. For Seedance 2.5 reference-to-video edit jobs, -1 or auto matches output length to the source clip (requires reference_video_urls on queue, or reference_video_total_duration on quote; source must be 4–30s).

Options disponibles: 1s, 2s, 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s, 16s, 17s, 18s, 19s, 20s, 21s, 22s, 23s, 24s, 25s, 26s, 27s, 28s, 29s, 30s, -1, 1 gen, auto, Auto

Exemple:

"10s"

consents · object

Optional provider-specific consent attestations. Required only for models that return a needs_consent response.

Show child attributes

negative_prompt · string

Optional negative prompt. The maximum length varies by model (default 2500 characters, up to 20000 for some models).

Maximum string length: 20000

Exemple:

"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. For Seedance 2.x reference-to-video edit/extend, adaptive or auto matches output aspect ratio to the source clip (requires reference_video_urls on queue, or reference_video_total_duration on quote).

Options disponibles: 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 9:21, 16:9, 21:9, adaptive, auto

Exemple:

"16:9"

omni_reference_task_type · enum<string>

Optional Seedance 2.5 reference-to-video task-type hint forwarded to BytePlus (auto | reference | edit | extend). Aliases editing→edit and extension→extend are accepted on the queue API. Pre-guides classification to reduce async TaskTypeConstraint errors. The prompt must still match the chosen type. When omitted, Venice infers from the prompt if reference_video_urls are present. Not supported on other models.

Options disponibles: auto, reference, edit, extend

Exemple:

"edit"

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.

Options disponibles: 256p, 360p, 480p, 540p, 580p, 720p, 1080p, 1440p, 2160p, 4k, 1x, 2x, 4x, 2K, 768P, true_1080p

Exemple:

"720p"

upscale_factor · enum<integer> · défaut: 2

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

Options disponibles: 1, 2, 4

Exemple:

2

enhancement_model · string

For enhancement models only. The provider-side enhancement model. Available values are listed per model in GET /models constraints.topaz.models.

Exemple:

"Proteus"

target_fps · integer

For enhancement models only. Target FPS for frame interpolation (16-120). Doubles the price on upscaling endpoints when ≥48; scales linearly on interpolation. Omit to keep the source frame rate.

Exemple:

60

softness · number

For enhancement models only. Softness level (1-5, sharpest to softest).

Plage requise: 1 <= x <= 5

Exemple:

3

creativity · number

For enhancement models only. How much new detail the model invents (0.0-1.0).

Plage requise: 0 <= x <= 1

Exemple:

0.5

realism · number

For enhancement models only. Bias generated detail toward photorealism (0.0-1.0).

Plage requise: 0 <= x <= 1

Exemple:

0.5

sharp · number

For enhancement models only. Output sharpness (0.0 softens, 0.5 neutral, 1.0 strong).

Plage requise: 0 <= x <= 1

Exemple:

0.5

compression · number

For enhancement models only. Compression artifact removal level (0.0-1.0).

Plage requise: 0 <= x <= 1

Exemple:

0.5

noise · number

For enhancement models only. Noise reduction level (0.0-1.0).

Plage requise: 0 <= x <= 1

Exemple:

0.5

halo · number

For enhancement models only. Halo reduction level (0.0-1.0).

Plage requise: 0 <= x <= 1

Exemple:

0.5

grain · number

For enhancement models only. Film grain amount (0.0-0.1).

Plage requise: 0 <= x <= 0.1

Exemple:

0

recover_detail · number

For enhancement models only. Recover original detail level (0.0-1.0).

Plage requise: 0 <= x <= 1

Exemple:

0.5

h264_output · boolean

For enhancement models only. Output H.264 instead of the default H.265.

Exemple:

false

output_format · enum<string>

For enhancement models only (SDR-to-HDR). Output container: mp4 (10-bit H265 HDR10) or prores (10-bit ProRes).

Options disponibles: mp4, prores

Exemple:

"mp4"

slowdown_factor · enum<integer>

For enhancement models only (frame interpolation). Slow-motion factor: 2 makes the output twice as long at the target FPS, up to 8x. Multiplies the billed duration.

Options disponibles: 1, 2, 4, 8

Exemple:

1

audio · boolean · défaut: true

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

Exemple:

true

image_url · string

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

Exemple:

"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.

Exemple:

"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.

Exemple:

"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.

Exemple:

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

reference_image_urls · string[]

For models with reference image support, up to 30 images for character/style consistency. Each must be a URL or data URL.

Maximum array length: 30

Exemple:

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

reference_video_urls · string[]

For models with reference video support (e.g. Seedance 2.0 R2V), up to 10 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: 10

Exemple:

["https://example.com/reference-clip.mp4"]

reference_audio_urls · string[]

For models with reference audio support (e.g. Seedance 2.0 R2V), up to 10 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: 10

Exemple:

["data:audio/mpeg;base64,SUQzBAAAAAA..."]

reference_document_urls · string[]

For models with document / webpage Omni-Reference (Wan 3.0), up to 1 URL. Document files and public webpage URLs are fetched by Venice and forwarded as type: "file" (≤100 MB). Each must be a URL or data URL.

Maximum array length: 1

Exemple:

["https://example.com/brief.pdf"]

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

Show child attributes

Exemple:

[
  {
    "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

Exemple:

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

keyframes · object[]

For keyframe-driven models. Up to 10 keyframe images pinned to frame positions in the generated 24 fps video. Each frame_index must be unique and no greater than duration × 24.

Maximum array length: 10

Show child attributes

Exemple:

[
  {
    "image_url": "data:image/png;base64,iVBORw0K...",
    "frame_index": 0
  },
  {
    "image_url": "data:image/png;base64,iVBORw0K...",
    "frame_index": 120
  }
]

Réponse

200

application/json

Video generation request queued successfully

model · string · requis

The ID of the model used for video generation.

Exemple:

"video-model-123"

queue_id · string · requis

The ID of the video generation request.

Exemple:

"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.