Skip to main content
POST
/api/v1/video/queue
Chame /video/quote para obter uma estimativa de preço e depois faça polling em /video/retrieve com o queue_id retornado até concluir. Modelos privados também retornam uma download_url para o vídeo finalizado. É uma URL de entrega de curta duração (algumas tentativas são aceitáveis caso um download caia); veja o guia de Geração de Vídeo para detalhes e para o DELETE opcional para privacidade.

Seedance 2.0 & 2.5

Para os modelos seedance-2-0-*-basic e seedance-2-5-*-basic (text-to-video, image-to-video, reference-to-video, além das variantes -fast-* do Seedance 2.0), veja o Guia do Seedance 2.0 & 2.5 para o modelo de quatro workflows (Reference / Edit / Extend / Stitch), valores aspect_ratio / duration correspondentes à origem, limites multimodais específicos por família, política de mídia da API pública e detalhes de preço.

Política de mídia pública do Seedance

Os modelos públicos do Seedance não utilizam atestação de consentimento (consents.seedance / needs_consent). Mídia com pessoas detectáveis pode ser rejeitada upstream. Use o app Venice ou o Studio para o conjunto completo de recursos do Seedance. Veja o guia do Seedance para detalhes.

Upscaling de vídeo

Para o modelo topaz-video-upscale, use upscale_factor (1, 2 ou 4) em vez de resolution e forneça uma video_url. Duração e FPS são detectados automaticamente a partir do arquivo de vídeo. Veja o Guia de Upscaling de Vídeo para detalhes e exemplos completos.

Autorizações

Authorization
string
header
obrigatório

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

Corpo

application/json

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

model
string
obrigatório

The model to use for video generation.

Exemplo:

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

prompt
string
obrigatório

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
Exemplo:

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

duration
enum<string>
obrigatório

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).

Opções disponíveis:
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
Exemplo:

"10s"

consents
object

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

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
Exemplo:

"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).

Opções disponíveis:
1:1,
2:3,
3:2,
3:4,
4:3,
4:5,
5:4,
9:16,
9:21,
16:9,
21:9,
adaptive,
auto
Exemplo:

"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 editingedit and extensionextend 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.

Opções disponíveis:
auto,
reference,
edit,
extend
Exemplo:

"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.

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

"720p"

upscale_factor
enum<integer>
padrão:2

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

Opções disponíveis:
1,
2,
4
Exemplo:

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.

Exemplo:

"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.

Exemplo:

60

softness
number

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

Intervalo obrigatório: 1 <= x <= 5
Exemplo:

3

creativity
number

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

Intervalo obrigatório: 0 <= x <= 1
Exemplo:

0.5

realism
number

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

Intervalo obrigatório: 0 <= x <= 1
Exemplo:

0.5

sharp
number

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

Intervalo obrigatório: 0 <= x <= 1
Exemplo:

0.5

compression
number

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

Intervalo obrigatório: 0 <= x <= 1
Exemplo:

0.5

noise
number

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

Intervalo obrigatório: 0 <= x <= 1
Exemplo:

0.5

halo
number

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

Intervalo obrigatório: 0 <= x <= 1
Exemplo:

0.5

grain
number

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

Intervalo obrigatório: 0 <= x <= 0.1
Exemplo:

0

recover_detail
number

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

Intervalo obrigatório: 0 <= x <= 1
Exemplo:

0.5

h264_output
boolean

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

Exemplo:

false

output_format
enum<string>

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

Opções disponíveis:
mp4,
prores
Exemplo:

"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.

Opções disponíveis:
1,
2,
4,
8
Exemplo:

1

audio
boolean
padrão:true

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

Exemplo:

true

image_url
string

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

Exemplo:

"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.

Exemplo:

"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.

Exemplo:

"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.

Exemplo:

"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
Exemplo:
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
Exemplo:
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
Exemplo:
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
Exemplo:
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
Exemplo:
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
Exemplo:
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
Exemplo:

Resposta

Video generation request queued successfully

model
string
obrigatório

The ID of the model used for video generation.

Exemplo:

"video-model-123"

queue_id
string
obrigatório

The ID of the video generation request.

Exemplo:

"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.