{"uid":"cap_0zzrAem-SZEeXvwrvtIhJ","slug":"agentutility-video-transcription-whisper-v3-83d051eb","name":"AgentUtility Video Transcription (Whisper v3)","description":"Transcribes any video URL to text with Whisper v3 large. Auto-detects 90+ languages and offers a translate-to-English mode. 60-min / 500MB max. Same backend as video-to-text under a clearer slug. Use it for video transcription, video to audio transcription, or video-to-text. For speaker labels, use the speaker-diarize endpoint.","url":"https://x402.agentutility.ai/video-transcribe","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"required":["media_url"],"properties":{"task":{"enum":["transcribe","translate"],"type":"string","description":"'transcribe' (default) keeps original language, or 'translate' to English."},"language":{"type":"string","description":"Source language hint (ISO code). Optional; auto-detected if omitted."},"media_url":{"type":"string","description":"URL of the video or audio file to transcribe. Max 60 minutes / 500MB."}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"task":{"type":"string"},"text":{"type":"string"},"duration_seconds":{"type":"integer"}}}}}}},"responseSchema":{"type":"json","example":{"task":"transcribe","text":"Hello world.","duration_seconds":23}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.1","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.33","reviews":0,"stars":null,"state":"rated"},"availabilityStatus":"unknown","priceObserved":{"p10Cents":"10.0000","medianCents":"10.0000","p90Cents":"10.0000","minCents":"10.0000","maxCents":"10.0000","p95Cents":"10.0000","sampleCount":6,"varies":false,"failureChargeRate":1},"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.1/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.1","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.1","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_fFKBgxfuPCpS1AsAa0Biy","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.1","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes any video URL to text using Whisper v3 large, with auto-detection of 90+ languages, optional English translation, and optional speaker diarization.","exampleAgentPrompt":"Transcribe this video for me — https://example.com/my-lecture.mp4 — it's in French but I want the transcript translated into English, and please separate out different speakers if you can.","exampleUseCases":[{"title":"Meeting recording to searchable transcript","prompt":"I have a recording of our team standup at https://storage.example.com/standup-2025-05-12.mp4 — can you transcribe it with speaker labels so I know who said what?"},{"title":"Foreign language video to English text","prompt":"Transcribe this Spanish-language interview at https://cdn.example.com/entrevista.mp4 and translate the transcript into English for me."},{"title":"Online lecture notes generation","prompt":"Pull the transcript from this lecture video at https://university.edu/lecture-week3.mp4 so I can turn it into study notes — the professor speaks pretty fast so I need accurate Whisper transcription."}],"resultDescription":"Returns the full text transcript of the video's spoken audio, including detected source language, optionally translated to English, with optional per-speaker segment labels and timestamps. Maximum video length is 60 minutes / 500 MB.","failureModes":["Video URL unreachable or returns non-200 — transcription fails with URL error","Video exceeds 60-minute or 500 MB limit — rejected with size/duration error","Unsupported audio codec or corrupted video file — returns processing error","Language not among the 90+ supported — may produce garbled output","Network timeout fetching large video files — request may time out"],"whenToPreferThis":"Choose this endpoint when you need high-accuracy transcription of a video file via URL, especially for multilingual content, foreign-language-to-English translation, or meeting recordings needing speaker attribution. It leverages Whisper v3 large, the highest-accuracy open model, and handles up to 60 minutes per call. Prefer it over generic STT APIs when language auto-detection or diarization is needed without pre-configuration.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":18,"lastUsedAt":"2026-09-05T14:50:09.483Z","lastSuccessfullyRanAt":"2026-09-05T14:50:09.483Z","lastHealthCheckAt":"2026-09-15T03:45:41.702Z","isFirstParty":false}