{"uid":"cap_cnHN3hmMbXZ5fXObUgPda","slug":"adam-hale-tools-short-audio-transcription-whisper-8652c2a2","name":"Adam Hale Tools: Short Audio Transcription (Whisper)","description":"Guides and free-to-run Apify actors for bulk tech stack lookup, sitemap URL export to CSV, TED and UK Find a Tender search, and RSS-to-JSON feed monitoring.","url":"https://tools.adamhaleworks.workers.dev/x402/v1/transcribe-short?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"Direct public URL of an audio file (MP3, WAV, M4A, OGG, FLAC or WebM), up to 2 MB. No YouTube or social media pages."},"vad":{"enum":["0","1"],"type":"string","description":"1 (default) filters silence with voice activity detection first; 0 turns it off."},"task":{"enum":["transcribe","translate"],"type":"string","description":"transcribe (default) or translate (into English)."},"language":{"type":"string","description":"Spoken language as an ISO 639-1 code (en, de, es…); detected when omitted."}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"vtt":"WEBVTT\n\n00:00.240 --> 00:01.260\n Yesterday,\n\n00:01.660 --> 00:03.360\n December\n\n…","task":"transcribe","text":"Yesterday, December 7, 1941, a state which will live in infamy. The United States of America was suddenly and deliberately attacked by naval and air forces of the Empire of Japan.","bytes":363717,"model":"@cf/openai/whisper-large-v3-turbo","finalUrl":"https://upload.wikimedia.org/wikipedia/commons/4/46/1941_Roosevelt_speech_pearlharbor_p1.ogg","mimeType":"audio/ogg","noSpeech":false,"segments":[{"end":12.84,"text":"Yesterday, December 7, 1941, a state which will live in infamy.","start":0.24},{"end":25.07,"text":"The United States of America was suddenly and deliberately attacked by naval and air forces of the Empire of Japan.","start":13.06}],"sourceUrl":"https://upload.wikimedia.org/wikipedia/commons/4/46/1941_Roosevelt_speech_pearlharbor_p1.ogg","wordCount":31,"durationSeconds":26.1,"detectedLanguage":"en","languageProbability":0.997}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","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":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ccFcvIMWJyl714fvbqNdW","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes or translates short public audio files (up to 2 MB) to text and WebVTT captions using Whisper large-v3-turbo, with optional voice activity detection and language detection.","exampleAgentPrompt":"Can you transcribe the audio at https://upload.wikimedia.org/wikipedia/commons/4/46/1941_Roosevelt_speech_pearlharbor_p1.ogg and give me the full text along with timestamped captions? Detect the language automatically.","exampleUseCases":[{"title":"Podcast episode transcript from URL","prompt":"I have a direct MP3 link to this week's podcast episode — can you transcribe it to text and give me the timestamped segments so I can create show notes? The URL is https://example.com/podcast/episode42.mp3"},{"title":"Translate foreign language audio to English","prompt":"I have an OGG audio file of a German speech at https://example.com/speech_de.ogg — please translate it into English text and give me the full transcript."},{"title":"Auto-caption a short voice memo","prompt":"Here's a public link to a voice memo WAV file: https://example.com/memo.wav — can you transcribe it and generate WebVTT captions with timestamps? Turn off voice activity detection since the whole clip is speech."}],"resultDescription":"Returns a JSON object containing: the full plain-text transcript, a WebVTT-formatted caption string with timestamps, an array of timestamped segments (start, end, text), detected language code, language detection probability, word count, audio duration in seconds, MIME type, file size in bytes, the model used (Whisper large-v3-turbo), and the resolved final URL of the audio file.","failureModes":["Audio file URL is not directly accessible (e.g. YouTube or social media page instead of direct file link) — returns error","Audio file exceeds 2 MB size limit — returns error","Unsupported audio format — only MP3, WAV, M4A, OGG, FLAC, WebM are accepted","noSpeech:true returned when no speech is detected in the audio","Network timeout if the audio URL is slow to respond","Invalid ISO 639-1 language code passed — may fall back to auto-detection or error"],"whenToPreferThis":"Choose this endpoint when you have a direct public URL to a short audio file (under 2 MB) and need fast, low-cost transcription or English translation with timestamped captions. It is ideal for voice memos, short podcast clips, recorded speeches, or any audio where WebVTT output and segment-level timestamps are needed. Prefer this over heavier transcription services when cost ($0.01/call), speed, and Whisper large-v3-turbo quality are priorities. Not suitable for YouTube links, social media URLs, or files over 2 MB.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-15T20:09:14.840Z","isFirstParty":false,"canonicalSlug":"adam-hale-tools-short-audio-transcription-whisper-8652c2a2"}