{"uid":"cap_SzA0gziuNkzEzPT_KngIH","slug":"agent-tools-video-transcription-upload-299f4d64","name":"Agent Tools – Video Transcription (Upload)","description":"Pay-per-call utilities for AI agents over x402, USDC on Base.","url":"https://agents.crowdspark.me/v1/video/transcribe/upload?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"task":{"enum":["transcribe","translate"],"type":"string"},"language":{"type":"string","description":"Optional ISO code, e.g. en"}}},"responseSchema":{"type":"json","example":{"task":"transcribe","text":"Hello and welcome to the show.","bytes":67000,"model":"whisper-large-v3-turbo","format":"mp4","language":"en","segments":[{"end":4.2,"text":"Hello and welcome to the show.","start":0}],"word_count":6,"duration_seconds":4.2}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.03","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":"$0.03/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_JkSqGd69GLTXcK1r-6tBZ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.03","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes or translates uploaded video files (MP4, QuickTime, WebM) into text, returning transcript, language, duration, segments, and WebVTT captions.","exampleAgentPrompt":"Can you transcribe this MP4 video I'm uploading and give me a full transcript with timestamps and WebVTT captions? The language is English.","exampleUseCases":[{"title":"Meeting recording to transcript","prompt":"I've got a 15-minute team meeting recorded as an MP4. Can you transcribe it and give me the full text along with timestamped segments so I can find specific moments?"},{"title":"Multilingual video captioning","prompt":"I have a Spanish-language webinar in QuickTime format — can you transcribe the audio and generate WebVTT captions for it so I can add subtitles?"},{"title":"Translate foreign-language video","prompt":"I uploaded a WebM video recorded in French. Can you translate the speech into English and give me the full transcript and segment timings?"}],"resultDescription":"Returns a JSON object containing: the task type, full transcript text, detected or specified language, video duration in seconds, word count, file format, model used (whisper-large-v3-turbo), an array of timed segments each with start/end timestamps and text, and WebVTT captions data. File size is also echoed back as bytes.","failureModes":["File exceeds 20 MB limit — request rejected","Unsupported video format — only MP4, QuickTime, WebM accepted","No audio track detected in video — empty or failed transcript","Corrupted or unreadable video bytes — parsing error","Invalid language ISO code — may fall back to auto-detection or error","Network timeout on large uploads — partial or failed response"],"whenToPreferThis":"Choose this endpoint when you have a raw video file (MP4, MOV, WebM) available as bytes or base64 and need a complete transcript with timestamped segments and WebVTT captions in a single call. Prefer it over URL-based transcription services when the video is local or not publicly accessible. The whisper-large-v3-turbo model provides high accuracy across many languages and supports both transcription and translation tasks at a low flat cost per call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-02T10:05:06.622Z","isFirstParty":false,"canonicalSlug":"agent-tools-video-transcription-upload-299f4d64"}