{"uid":"cap_l87GOxiT-p_a7b-z_y-9b","slug":"haven-video-sound-generator-3fb9422e","name":"Haven Video Sound Generator","description":"Haven is a private AI agent for your home. Join the waitlist for h1 speaker updates and early app access.","url":"https://api.havenagent.ai/x402/api/v1/video-sound","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"prompt":{"type":"string","maxLength":2000,"minLength":1},"mediaType":{"enum":["image/png","image/jpeg"],"type":"string"},"imageBase64":{"type":"string","description":"base64 image bytes, no data-URI prefix"},"durationSeconds":{"type":"integer","default":5,"maximum":10,"minimum":4}}},"responseSchema":{"type":"json","example":{"kind":"video_sound","jobId":"00000000-0000-0000-0000-000000000000","status":"queued","resultUrl":"https://api.havenagent.ai/x402/api/v1/video-sound/jobs/00000000-0000-0000-0000-000000000000/result","statusUrl":"https://api.havenagent.ai/x402/api/v1/video-sound/jobs/00000000-0000-0000-0000-000000000000","etaSeconds":900,"aiDisclosure":{"label":"AI Generated","termsUrl":"https://havenagent.ai/terms/terms-of-service","statement":"AI Generated: this video is machine-generated by Haven Media and does not depict real events. Use terms: https://havenagent.ai/terms/terms-of-service","embeddedIn":"mp4-metadata","aiGenerated":true},"pollBudgetSeconds":1800}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"1.5","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","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":"$1.5/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"1.5","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"1.5","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_p1Lp6hJ9fEpEBwrXWBGnU","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"1.5","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Generates an AI-created video with synchronized sound from an image and text prompt, returned as an async job","exampleAgentPrompt":"Take this image of my living room and generate a 5-second video with ambient sound — like a cozy evening vibe — using Haven's video-sound generator.","exampleUseCases":[{"title":"Animated home ambiance clip","prompt":"I have a JPEG photo of my backyard at sunset. Can you turn it into a short 6-second video with nature sounds using Haven? Here's the image in base64."},{"title":"Real estate listing video snippet","prompt":"Take this PNG of our open kitchen and make a 5-second video clip with light background sound for our listing — the prompt should emphasize 'bright modern kitchen, welcoming atmosphere.'"},{"title":"Social media home tour teaser","prompt":"I want to create a quick 8-second animated video from this living room photo with relaxing music sounds — something that feels like a peaceful home tour teaser for Instagram."}],"resultDescription":"An asynchronous job response containing a jobId, a statusUrl to poll for completion, a resultUrl where the finished MP4 video can be downloaded, an estimated ETA of up to 900 seconds, and embedded AI disclosure metadata (label, statement, terms URL) baked into the MP4 metadata indicating the content is machine-generated.","failureModes":["Invalid or malformed base64 image data causing rejection","Image media type mismatch (sending JPEG but declaring PNG or vice versa)","Prompt exceeding 2000-character limit","Duration outside allowed range of 4–10 seconds","Payment failure via x402 protocol resulting in 402 response","Job timeout or failure detected via status polling beyond pollBudgetSeconds (1800s)","Result URL returning empty or error if generation fails on the backend"],"whenToPreferThis":"Choose this endpoint when you need to generate a short AI video (4–10 seconds) with synchronized sound starting from a still image and a descriptive text prompt. It is specifically suited for home-context media generation (e.g., ambient clips, property visuals) and produces MP4 output with embedded AI disclosure metadata. Prefer this over text-only or image-only generation endpoints when the output must include both visual motion and audio. Note the async/polling model means it is not suitable for real-time or latency-sensitive workflows.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T09:15:22.314Z","isFirstParty":false}