{"uid":"cap_V0WbEhh2kUvdyXdYhv_l5","slug":"voxsift-transcription-api-7cf3909c","name":"VoxSift Transcription API","description":"Metered speaker-aware audio transcription for autonomous agents. Submit a public HTTPS audio or video URL and receive deterministic transcript JSON with timestamps, optional speaker diarization, confidence metadata, and actual-duration x402 settlement.","url":"https://voxsift-x402.fly.dev/v1/transcribe","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"url":{"type":"string","format":"uri"},"diarize":{"type":"boolean","default":true},"language":{"type":"string"}}},"responseSchema":{"type":"json","example":{"text":"Example transcript text.","billing":{"scheme":"x402-upto","charged_usd":"$0.002084","charged_atomic":"2084"},"language":"en","segments":[{"end":4.2,"text":"Example transcript text.","start":0,"speaker":"A","confidence":0.96}],"confidence":0.96,"request_id":"3d0ee76d-8337-41c6-bf44-e1eb1547f249","duration_seconds":12.5,"source_duration_seconds":12.5}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.2","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":"$0.2/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.2","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.2","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_27NXiGIYJ2orIEEEq4DuT","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.2","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes a public HTTPS audio or video URL into structured JSON with timestamps, optional speaker diarization, and confidence metadata.","exampleAgentPrompt":"Transcribe this podcast episode for me — https://example.com/podcast/ep42.mp3 — with speaker diarization turned on and language set to English (en).","exampleUseCases":[{"title":"Podcast episode transcription with speakers","prompt":"Can you transcribe this podcast at https://mypodcast.com/episodes/episode-15.mp3 into structured text with speaker labels and timestamps? Use English as the language."},{"title":"Meeting recording to searchable notes","prompt":"I have a recorded Zoom call at https://recordings.mycompany.com/team-standup-2024-06-10.mp4 — please transcribe it with speaker diarization so I can tell who said what."},{"title":"Accessibility captions for video content","prompt":"Transcribe the video at https://cdn.mysite.com/webinar-june.mp4 into timestamped JSON with confidence scores — I need the text broken out by speaker for generating captions."}],"resultDescription":"Returns structured JSON containing the full transcript broken into utterances, each with start/end timestamps, speaker identifiers (when diarization is enabled), confidence scores per segment, and the actual audio duration for billing settlement purposes.","failureModes":["URL is not publicly accessible or requires authentication — returns an error indicating the resource could not be fetched","Non-audio/video URL or unsupported media format — returns format error","Network timeout fetching long media files — may return a timeout or partial result error","Unsupported or unrecognized language code — may default to auto-detect or return a validation error","Audio too short or silent — may return an empty transcript or low-confidence result"],"whenToPreferThis":"Choose VoxSift when you need structured JSON transcription output with per-utterance timestamps and confidence metadata from a publicly accessible audio or video URL, especially when speaker diarization is required. Ideal for automating podcast indexing, meeting summarization, accessibility captioning pipelines, or any workflow where machine-readable timestamped speech output is needed. Prefer this over generic STT APIs when you want actual-duration-based billing and speaker-separated utterances in a single call.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:38:18.290Z","isFirstParty":false}