{"uid":"cap_A_JfugTMY24XDBVL-pdwp","slug":"x402-nvidia-active-speaker-detection-api-f07aa1fb","name":"X402-NVIDIA Active Speaker Detection API","description":"Access 48+ NVIDIA NIM AI models via x402 micropayments. Chat completions, vision, safety, translation, and more.","url":"https://x402-nvidia.vercel.app/api/active-speaker-detection","method":"POST","headers":{},"bodySchema":null,"responseSchema":{"type":"object","example":{"choices":[{"message":{"role":"assistant","content":"Hello!"}}]},"properties":{"choices":{"type":"array","description":"Model responses"}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.131141","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":"$0.131141/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.131141","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.131141","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_uSC-NsgPFWxU7kdGcjJRp","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.131141","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Detects active speakers in audio or video content using NVIDIA NIM AI models, accessed via x402 micropayments.","exampleAgentPrompt":"Can you run active speaker detection on this audio clip and tell me who is speaking at each moment? Use the NVIDIA NIM model via the x402-nvidia service.","exampleUseCases":null,"resultDescription":"Returns a choices array containing model responses with detected active speaker labels and timestamps or segmentation data indicating which speaker is active at which points in the media content.","failureModes":["Invalid or missing media input returns a 400 error","Payment failure via x402 micropayment results in a 402 response blocking access","Model unavailability returns a 503 or timeout error","Malformed input schema causes a 422 unprocessable entity error","Unsupported audio/video format may result in processing failure"],"whenToPreferThis":"Choose this endpoint when you need NVIDIA NIM-powered active speaker detection and want to pay per-call via x402 USDC micropayments without a subscription, especially useful for sporadic or low-volume speaker detection tasks.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T12:53:08.104Z","isFirstParty":false}