{"uid":"cap_W9CEGYNNokgdaTRzEwZVU","slug":"citiview-speech-to-text-transcription-whisper-large-v3-turbo-adc3a122","name":"Citiview 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. Priced by length: $0.002 + $0.0015 per minute of max_minutes (default 6, up to 30). Also callable as GET with the same fields as query parameters.","url":"https://agents.citiviewgroup.com/v1/transcribe?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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":"0.011","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":"$0.011/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.011","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.011","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_m0roaX0cq8-9gPEvgaKHV","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.011","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 files from a public URL or base64-encoded audio, returning the full transcript, detected language, timed segments, and WebVTT subtitles.","exampleAgentPrompt":"Can you transcribe this podcast episode for me? Here's the public MP3 URL: https://example.com/episode42.mp3 — I'd also like the WebVTT subtitles and timestamped segments.","exampleUseCases":[{"title":"Podcast episode to searchable text","prompt":"I have a podcast episode hosted at https://mypodcast.com/ep10.mp3 — can you transcribe it to text and give me the timed segments so I can make it searchable?"},{"title":"Auto-generate video captions","prompt":"Can you generate WebVTT subtitles for this video at https://cdn.example.com/webinar.mp4? I need the captions synced with timestamps for upload to our video platform."},{"title":"Detect language of foreign audio","prompt":"I have an audio recording at https://media.example.com/interview.wav and I'm not sure what language is being spoken — can you transcribe it and tell me the detected language?"}],"resultDescription":"Returns the full transcript text, the detected spoken language code, an array of timed segments with start/end timestamps and text, and a WebVTT-formatted subtitle string suitable for embedding in video players.","failureModes":["File exceeds 20 MB limit — returns an error indicating file too large","URL is not publicly accessible or returns a non-200 response — returns a fetch/access error","Unsupported audio/video format — only mp3, wav, m4a, ogg, webm, mp4 are supported","base64 input is malformed or corrupt — returns a decoding error","Language hint is an invalid ISO 639-1 code — may degrade detection accuracy or return an error","Payment not provided or insufficient — returns 402 Payment Required"],"whenToPreferThis":"Choose this endpoint when you need fast, accurate transcription with timestamps and WebVTT subtitles in a single call, especially when your source is a publicly accessible audio/video URL or base64 audio up to 20 MB. It is ideal for multilingual content since Whisper large-v3-turbo auto-detects language. Prefer it over raw Whisper integrations when you want an agent-ready, pay-per-call API with no setup.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-14T06:48:37.006Z","isFirstParty":false,"canonicalSlug":"citiview-speech-to-text-transcription-whisper-large-v3-turbo-adc3a122"}