{"uid":"cap_yUnwz3iTZGBMr1yGtSCdg","slug":"transcript-audio-video-transcription-api-b3ecbb6a","name":"Transcript+ Audio/Video Transcription API","description":"Transcript+: audio/video URL or upload to a speaker-labelled (diarized) transcript, summary, chapters and SRT/VTT captions. Priced per audio minute.","url":"https://seenly-transcript-plus.vercel.app/api/transcribe?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","properties":{"url":{"type":"string","description":"Public http(s) URL of an audio or video file (max 100 MB, 60 min)."},"file":{"type":"object","properties":{"base64":{"type":"string"},"filename":{"type":"string"}},"description":"Inline file instead of url (max 4 MB)."},"format":{"enum":["json","srt","vtt","text"],"type":"string","default":"json"},"diarize":{"type":"boolean","default":true},"summary":{"type":"boolean","default":true},"language":{"type":"string","description":"Optional locale hint, e.g. en-US"},"maxMinutes":{"type":"integer","description":"Refuse (before payment) if the audio is longer."}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"billing":{"totalUsd":"0.05","billableMinutes":5},"summary":{"title":"...","chapters":[]},"captions":{"srt":"...","vtt":"..."},"segments":[{"end":8.5,"text":"...","start":0.4,"speaker":"S1"}],"speakers":[{"id":"S1"}],"durationSec":249.1}},"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_53iB3DBxu2lSvcXorgq40","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts audio or video (URL or uploaded file) into a speaker-labelled diarized transcript, summary, chapter markers, and SRT/VTT captions","exampleAgentPrompt":"Transcribe this podcast episode for me — https://example.com/podcast.mp3 — with speaker labels and a summary, and give me the output as SRT captions too.","exampleUseCases":[{"title":"Meeting recording to searchable notes","prompt":"I have a recorded Zoom call at https://storage.example.com/meeting.mp4 — can you transcribe it with speaker labels, generate a summary, and break it into chapters so I can quickly navigate the key topics?"},{"title":"Podcast subtitle generation","prompt":"Generate SRT caption files for this podcast episode at https://cdn.example.com/episode42.mp3 so we can upload them to our video platform — diarize it too so listeners can follow who's speaking."},{"title":"Interview transcript for journalism","prompt":"Transcribe this journalist interview audio at https://files.example.com/interview.m4a with full speaker diarization — the recording is under 30 minutes — and give me the transcript as plain text with a summary at the top."}],"resultDescription":"Returns a structured JSON object (or SRT/VTT/text depending on format parameter) containing the full speaker-labelled transcript with timestamps, a prose summary of the content, timestamped chapter markers, and optionally SRT or VTT caption blocks ready for upload to video platforms.","failureModes":["Audio/video file exceeds 100 MB or 60-minute limit — request rejected before payment","Inline base64 file exceeds 4 MB limit — request rejected","maxMinutes guard triggers if audio is longer than specified — rejected before payment","Unsupported audio/video format or corrupted file — transcription fails","Public URL unreachable or requires authentication — download fails","Language hint not recognized — may fall back to auto-detection with reduced accuracy","x402 payment not completed — endpoint returns 402 and transcription does not proceed"],"whenToPreferThis":"Choose this endpoint when you need speaker-attributed (diarized) transcripts alongside summaries and chapter markers in a single call, especially for meetings, interviews, or podcasts. It accepts both remote URLs (up to 100 MB / 60 min) and small inline file uploads and outputs multiple formats (JSON, SRT, VTT, text) in one request. Prefer it over bare transcription APIs when you need the full package — diarization, summary, and captions — without chaining multiple services.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":1,"lastUsedAt":"2026-10-12T22:57:27.946Z","lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-19T17:35:03.025Z","isFirstParty":false,"canonicalSlug":"transcript-audio-video-transcription-api-b3ecbb6a"}