{"uid":"cap_EBwEcqhsZMTUI_kLyhRIc","slug":"sitecheck-media-transcript-speech-to-text-8e2abcad","name":"SiteCheck Media Transcript (Speech-to-Text)","description":"Speech to text from a media link: TikTok, X, SoundCloud, Facebook, Dailymotion, podcasts, Drive or Dropbox links, direct audio or video files. Text, timestamped segments, language, duration; speaker labels on request. Price from maxMinutes (default 5, up to 120): direct file up to 25 MB $0.001 + $0.0006/min, other links $0.002 + $0.0009/min, speakers=1 $0.01/min. Longer media is refused unpaid. YouTube returns captions. No speech is a 404, not charged.","url":"https://api.sitecheck-api.workers.dev/api/media/transcript?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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 link to the video, audio file or podcast episode (http or https)"},"language":{"type":"string","description":"Spoken language code such as en, tr or pt-BR (optional, detected by default)"},"speakers":{"type":"string","description":"1 = label the speakers (optional; $0.01 per minute of maxMinutes)"},"maxMinutes":{"type":"string","description":"Longest media to accept, 1 to 120, default 5. Sets the price: a direct audio or video file up to 25 MB $0.001 + $0.0006 per minute, other links $0.002 + $0.0009 per minute"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"text":"Hello? Hello?","model":"deepgram nova-3","title":"Scramble up ur name & I’ll try to guess it😍❤️ #foryoupage #petsoftikt...","method":"speech-to-text","source":"https://www.tiktok.com/@scout2015/video/6718335390845095173","language":"en","platform":"tiktok.com","segments":[{"end":7.6,"text":"Hello?","start":6.72,"speaker":null},{"end":8.88,"text":"Hello?","start":8.24,"speaker":null}],"checkedAt":"2026-10-15T08:13:21.102Z","maxMinutes":10,"source_note":"Audio downloaded with yt-dlp and transcribed by Deepgram","speakerLabels":false,"durationSeconds":10.8}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.0065","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":"$0.0065/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0065","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.0065","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_DVN3fMVf0obk-t5PjDclt","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.0065","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 into text segments using Deepgram, with optional speaker labeling and language detection","exampleAgentPrompt":"Can you transcribe this podcast episode for me? Here's the URL: https://example.com/episode42.mp3 — transcribe up to 30 minutes, label the different speakers, and use English as the language.","exampleUseCases":[{"title":"Podcast episode transcription","prompt":"Transcribe this podcast episode for me — the URL is https://podcasts.example.com/ep100.mp3, it's in English, and please label who's speaking so I can tell the host and guest apart. Allow up to 60 minutes."},{"title":"Social media video to text","prompt":"I need the full transcript of this TikTok video: https://www.tiktok.com/@scout2015/video/6718335390845095173 — just the spoken words, no need for speaker labels, and keep it under 5 minutes."},{"title":"Multilingual audio file conversion","prompt":"Can you transcribe this Portuguese audio file at https://cdn.example.com/entrevista.mp3? The spoken language is pt-BR and I only need the first 10 minutes — no speaker labeling needed."}],"resultDescription":"Returns a JSON object containing the full transcript text, an array of timestamped segments (each with start time, end time, text, and optional speaker label), detected language, media title, source platform, duration in seconds, and the Deepgram model used. Also includes whether speaker labels were applied and the max minutes processed.","failureModes":["URL is not publicly accessible or returns a non-200 status","Audio/video format not supported by yt-dlp","Media duration exceeds the specified maxMinutes cap","Language detection fails for low-quality or silent audio","Network timeout for very large files","Deepgram API error causing partial or empty transcript"],"whenToPreferThis":"Choose this endpoint when you need to transcribe audio or video from any public URL — including social media platforms like TikTok, YouTube, or podcasts — especially when you need timestamped segments or speaker diarization. It is particularly useful for media hosted on platforms supported by yt-dlp. Prefer it over generic STT APIs when you need automatic platform detection, title extraction, and pay-per-use pricing with per-minute granularity.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-16T12:43:08.518Z","isFirstParty":false,"canonicalSlug":"sitecheck-media-transcript-speech-to-text-8e2abcad"}