{"uid":"cap_JBmzO_j7DhYX6CXG7f3iV","slug":"agent-hub-speech-to-text-transcription-whisper-large-v3-turbo-198273b2","name":"Agent Hub Speech-to-Text Transcription (Whisper Large v3 Turbo)","description":"Speech to text (Whisper large v3 turbo). Send a public audio/video URL or base64 audio (max 20 MB); get the transcript, detected language, timed segments and WebVTT subtitles. Also callable as GET with the same fields as query parameters.","url":"https://agents.torbrooknews.com/v1/transcribe?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","properties":{"url":{"type":"string","description":"Public URL of an audio or video file (mp3, wav, m4a, ogg, webm, mp4)"},"language":{"type":"string","description":"Optional ISO 639-1 hint, e.g. en"},"audio_base64":{"type":"string","description":"Alternative to url: base64 audio bytes"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","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":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_OjfZxRzucMrQJkMhYRi7b","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes audio or video from a public URL or base64-encoded audio into text, returning the transcript, detected language, timed segments, and WebVTT subtitles using Whisper large v3 turbo.","exampleAgentPrompt":"Can you transcribe this podcast episode for me? The audio file is at https://example.com/episode42.mp3 — I think it's in English but please detect the language and give me the full transcript along with WebVTT subtitles and timed segments.","exampleUseCases":[{"title":"Podcast episode captioning","prompt":"I have a podcast episode hosted at https://mypodcast.com/ep10.mp3 — can you transcribe it and give me WebVTT subtitle captions I can attach to the video version?"},{"title":"Meeting recording transcription","prompt":"Here's a link to our recorded team meeting: https://storage.example.com/meeting-2024-06-01.webm — please transcribe the whole thing, detect who's speaking in what language, and give me timed segments so I can find specific moments easily."},{"title":"Multilingual audio language detection","prompt":"I have a base64-encoded audio clip — I'm not sure what language the speaker is using. Can you transcribe it and tell me what language was detected along with the transcript?"}],"resultDescription":"Returns the full transcript text, the auto-detected language code (ISO 639-1), timed transcript segments with start/end timestamps, and WebVTT subtitle content ready for embedding in video players.","failureModes":["Audio or video URL is not publicly accessible — returns an error indicating the file could not be fetched","File exceeds 20 MB limit — returns a payload-too-large error","Unsupported file format (not mp3, wav, m4a, ogg, webm, or mp4) — returns an unsupported format error","Base64 audio is malformed or corrupted — returns a decoding error","Network timeout fetching a slow remote URL — returns a timeout error","Payment not included or insufficient — returns HTTP 402 Payment Required"],"whenToPreferThis":"Choose this endpoint when you need a pay-per-call, no-subscription speech-to-text solution that returns not just a raw transcript but also timed segments and ready-to-use WebVTT subtitles in a single call. It is especially well-suited for agents processing podcast episodes, video recordings, or voice memos from public URLs without requiring an OpenAI API key. Prefer it over self-hosted Whisper when you want a hosted, on-demand solution billed at $0.02 USDC per call via x402.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T12:45:53.004Z","isFirstParty":false,"canonicalSlug":"agent-hub-speech-to-text-transcription-whisper-large-v3-turbo-198273b2"}