{"uid":"cap_CPz-FRn4FHkKqTj3K7az9","slug":"venice-ai-video-generation-queue-0d849ebc","name":"Venice AI Video Generation Queue","description":"Queue video generation.","url":"https://api.venice.ai/api/v1/video/queue?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","required":["model","prompt","duration"],"properties":{"audio":{"type":"boolean","default":true,"example":true,"description":"For models which support audio generation and configuration. Defaults to true."},"model":{"type":"string","example":"seedance-2-0-text-to-video","description":"The model to use for video generation."},"prompt":{"type":"string","example":"Commerce being conducted in the city of Venice, Italy.","maxLength":10000,"minLength":1,"description":"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)."},"duration":{"enum":["2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","18s","20s","25s","30s","1 gen","Auto"],"type":"string","example":"5s","description":"The duration of the video to generate. Available options vary by model."},"elements":{"type":"array","items":{"type":"object","properties":{"video_url":{"type":"string"},"frontal_image_url":{"type":"string"},"reference_image_urls":{"type":"array","items":{"type":"string"},"maxItems":3}}},"example":[{"frontal_image_url":"data:image/png;base64,iVBORw0K...","reference_image_urls":["data:image/png;base64,iVBORw0K..."]}],"maxItems":4,"description":"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."},"audio_url":{"type":"string","example":"data:audio/mpeg;base64,SUQzBAA...","description":"For models that support audio input, background music. Must be a URL or data URL. Supported: WAV, MP3. Max: 30s, 15MB."},"image_url":{"type":"string","example":"data:image/png;base64,iVBORw0K...","description":"For image-to-video models, the reference image. Must be a URL (http/https) or a data URL (data:image/...)."},"video_url":{"type":"string","example":"data:video/mp4;base64,AAAAFGZ0eXA...","description":"For models that support video input (video-to-video, upscale). Must be a URL or data URL. Supported: MP4, MOV, WebM."},"resolution":{"enum":["256p","360p","480p","540p","580p","720p","1080p","1440p","2160p","4k","2x","4x","true_1080p"],"type":"string","example":"720p","description":"The resolution of the video. Available options vary by model. Some models do not support resolution. Use upscale_factor for upscale models."},"aspect_ratio":{"enum":["1:1","2:3","3:2","3:4","4:3","9:16","16:9","21:9"],"type":"string","example":"16:9","description":"The aspect ratio of the video. Available options vary by model. Some models do not support aspect_ratio."},"end_image_url":{"type":"string","example":"data:image/png;base64,iVBORw0K...","description":"For models that support end images or transitions, the end frame image. Must be a URL or data URL."},"upscale_factor":{"enum":[1,2,4],"type":"integer","default":2,"example":2,"description":"For upscale models only. 1 = quality enhancement, 2 = double resolution (default), 4 = quadruple."},"negative_prompt":{"type":"string","example":"low resolution, error, worst quality, low quality, defects","maxLength":10000,"description":"Optional negative prompt. The maximum length varies by model (default 2500 characters, up to 10000 for some models)."},"scene_image_urls":{"type":"array","items":{"type":"string"},"example":["data:image/png;base64,iVBORw0K..."],"maxItems":4,"description":"For models with advanced element support. Up to 4 scene reference images. Reference in prompt as @Image1, @Image2, etc."},"reference_audio_urls":{"type":"array","items":{"type":"string"},"example":["data:audio/mpeg;base64,SUQzBAAAAAA..."],"maxItems":3,"description":"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."},"reference_image_urls":{"type":"array","items":{"type":"string"},"example":["data:image/png;base64,iVBORw0K..."],"maxItems":9,"description":"For models with reference image support, up to 9 images for character/style consistency. Each must be a URL or data URL."},"reference_video_urls":{"type":"array","items":{"type":"string"},"example":["https://example.com/reference-clip.mp4"],"maxItems":3,"description":"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."}},"description":"Request body for video generation. Available fields and valid values vary by model."},"responseSchema":{"type":"object","required":["model","queue_id"],"properties":{"model":{"type":"string","example":"video-model-123","description":"The ID of the model used for video generation."},"queue_id":{"type":"string","example":"123e4567-e89b-12d3-a456-426614174000","description":"The ID of the video generation request."},"download_url":{"type":"string","description":"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."}},"additionalProperties":false},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"10","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$10/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"10","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"10","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Zm_Ml2Fc0CQY_Xzp8Zflo","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"10","costPer":"request","priority":0,"asset":"0x833589fcd6edb6e08f4c7c32d4f71b54bda02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Queues a new AI video generation request, returning a queue ID for tracking the async result.","exampleAgentPrompt":"Generate a 5-second AI video of 'a canal gondola gliding through Venice, Italy at golden hour' using the seedance-2-0-text-to-video model, with audio enabled.","exampleUseCases":null,"resultDescription":"Returns a JSON object with the model ID used, a queue_id UUID for polling the job status, and optionally a pre-signed download_url (valid 24 hours) for VPS-backed models where the video can be fetched once status is COMPLETED.","failureModes":["402 Payment Required — insufficient USDC balance, includes top-up instructions","400 Bad Request — missing required fields (model, prompt, duration) or invalid enum value for duration","400 Bad Request — prompt exceeds maximum length for chosen model","422 Unprocessable Entity — invalid image_url or video_url format (must be http/https or data URL)","401 Unauthorized — missing or invalid Bearer token or X-Sign-In-With-X header","429 Too Many Requests — rate limit exceeded"],"whenToPreferThis":"Use this endpoint when you need to generate AI video from text prompts or reference images/videos via the Venice AI platform, especially when you want async queue-based processing (poll for results separately), need model flexibility (Seedance, Kling, etc.), or are paying per-call via x402 wallet-based micropayments. Prefer over alternatives when the user needs configurable duration, audio input, or multi-element character references.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-11T12:47:43.654Z","isFirstParty":false,"canonicalSlug":"venice-ai-video-generation-queue-0d849ebc"}