{"uid":"cap__SUzz0EEzLmv92V2jwTHu","slug":"agent-hub-speech-to-text-whisper-large-v3-turbo-1b181010","name":"Agent Hub Speech-to-Text (Whisper Large v3 Turbo)","description":"OpenAI-compatible speech to text (Whisper large v3 turbo): multipart file upload exactly like OpenAI /v1/audio/transcriptions, with response_format json, text, srt, vtt or verbose_json. Also accepts a public audio url. Up to 20 MB, flat price, no API key. Also callable as GET with the same fields as query parameters.","url":"https://agents.torbrooknews.com/v1/audio/transcriptions?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":"Public audio file URL"},"language":{"type":"string"},"response_format":{"type":"string","description":"json | text | srt | vtt | verbose_json"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"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_EXM0OTNal-hc_vKEVNjZY","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 audio files or public audio URLs to text using Whisper large v3 turbo, returning output in json, text, srt, vtt, or verbose_json formats","exampleAgentPrompt":"Can you transcribe the audio at https://example.com/recording.mp3 and give me the result as an SRT subtitle file?","exampleUseCases":[{"title":"Podcast episode transcription","prompt":"Transcribe this podcast episode for me — the audio is at https://mypodcast.com/episode42.mp3 — and return the full text transcript in plain text format."},{"title":"Auto-generate video captions","prompt":"I need VTT captions for this interview recording at https://cdn.mysite.com/interview.wav so I can add them to my video player — can you generate those?"},{"title":"Multilingual meeting transcription","prompt":"Please transcribe this French meeting recording at https://storage.mycompany.com/meeting-fr.mp3 and return verbose JSON so I can see word-level timestamps — the language is French."}],"resultDescription":"Returns the transcription of the audio in the requested format: plain text ('text'), JSON object with a 'text' field ('json'), SRT subtitle format ('srt'), WebVTT subtitle format ('vtt'), or a detailed JSON object including segments and timestamps ('verbose_json').","failureModes":["Audio file exceeds 20 MB limit — request rejected","Invalid or inaccessible public URL — cannot fetch audio","Unsupported audio format — transcription fails","Incorrect response_format value — may return error or default format","Network timeout for large files — partial or no response"],"whenToPreferThis":"Choose this endpoint when you need a flat-rate ($0.01 USDC), no-API-key speech-to-text solution compatible with the OpenAI Whisper API, especially when you want multiple output formats (SRT, VTT, verbose_json) or need to transcribe from a public URL without uploading a file. Prefer over OpenAI directly when avoiding API key management or when cost predictability matters.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T12:46:38.960Z","isFirstParty":false,"canonicalSlug":"agent-hub-speech-to-text-whisper-large-v3-turbo-1b181010"}