{"uid":"cap_ljkyG6smVlXHaC5TdPOC_","slug":"x402-deployer-x402-deployer-workers-dev-7c509bf1","name":"Audio/Video Transcription via Whisper v3","description":"Video transcription / video to audio transcription / video to text / transcribe video / video speech-to-text / video ASR. Whisper v3 large transcription for any video URL — extracts audio internally. Auto-detects 90+ languages. Translate-to-English mode. 60-min / 500MB max. Speaker diarization optional.","url":"https://x402-deployer.x402-deployer.workers.dev/video-to-text","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":null,"example":{"request":{"input":{"body":{"task":"transcribe","language":"en","media_url":"https://www.soundhelix.com/examples/mp3/SoundHelix-Song-1.mp3"},"type":"http","method":"POST","bodyType":"json"}},"response":{"task":"transcribe","text":"♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪♪♪ ♪♪ ♪♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ Thank you.","chunks":[{"text":"♪ ♪ ♪ ♪ ♪ ♪ ♪","timestamp":[0.02,63.92]},{"text":"♪♪♪","timestamp":[66.02,85.56]},{"text":"♪♪ ♪♪","timestamp":[86.1,131.06]},{"text":"♪ ♪ ♪ ♪ ♪ ♪ ♪","timestamp":[133.72,245.04]},{"text":"♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪","timestamp":[246.04,348.3]},{"text":"Thank you.","timestamp":[350.24,369.98]}],"source_url":"https://www.soundhelix.com/examples/mp3/SoundHelix-Song-1.mp3","duration_seconds":372.715083,"detected_languages":null}},"exampleRequest":{"task":"transcribe","language":"en","media_url":"https://www.soundhelix.com/examples/mp3/SoundHelix-Song-1.mp3"},"tags":["x402"],"displayCostAmount":"0.1","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","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":"$0.1/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_sO5pEIN_JAo6brBR8xk78","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 audio or video from a URL into text using OpenAI Whisper v3","exampleAgentPrompt":"Can you transcribe the audio from this podcast episode for me? Here's the URL: https://example.com/episode42.mp3 — I need the full spoken text.","exampleUseCases":null,"resultDescription":"Returns a full text transcript of the spoken content in the provided audio or video URL, produced by Whisper v3.","failureModes":["Invalid or inaccessible URL returns an error","Unsupported media format may fail transcription","Very long audio files may time out","Non-audio/video URLs will fail to process","Network errors fetching the media URL"],"whenToPreferThis":"Use this endpoint when you need to extract speech-to-text from any publicly accessible audio or video URL, especially when you want raw transcription without summarization. If you also need a summary, prefer the sibling video summarizer endpoint. Best for podcasts, recorded meetings, video lectures, or any spoken-word media accessible via URL.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T03:45:38.813Z","isFirstParty":false}