{"uid":"cap_gbh3zMRLQPjoJhcygyj19","slug":"sift-web-tools-speech-to-text-transcription-020bea2c","name":"Sift Web Tools – Speech-to-Text Transcription","description":"Speech to text from an audio or video file URL (up to 5 minutes), with timestamps, SRT or VTT. Transcribes speech in an audio or video file (mp3, wav, m4a, mp4, webm and more; up to 80 MB and 5 minutes) with OpenAI Whisper running on our own servers. Auto-detects the language (99 languages). Returns text with segment timestamps, or ready-made SRT or VTT subtitles.","url":"https://sift.srv1996466.hstgr.cloud/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","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","required":["url"],"properties":{"url":{"type":"string","description":"Audio or video file URL"},"format":{"type":"string","description":"json, text, srt or vtt (default json)"},"language":{"type":"string","description":"Two-letter language code, e.g. en (default auto-detect)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":{"type":"json","example":{"text":"The quick brown fox jumps over the lazy dog.","language":"en","segments":[{"end":3.2,"text":"The quick brown fox jumps over the lazy dog.","start":0}],"duration_s":4.1}},"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_P7XO6YG5QCIW8oyCbM8dK","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 speech from an audio or video file URL using OpenAI Whisper, returning timestamped text, SRT, or VTT subtitles in up to 99 languages.","exampleAgentPrompt":"Can you transcribe the audio at https://example.com/interview.mp3 and give me the result as an SRT file with timestamps?","exampleUseCases":[{"title":"Podcast episode transcript generation","prompt":"Transcribe this podcast episode for me: https://example.com/episode42.mp3 — I need the full text with timestamps in JSON format, auto-detect the language."},{"title":"Video subtitle file creation","prompt":"Generate VTT subtitles for this webinar recording at https://example.com/webinar.mp4 so I can add captions to the video."},{"title":"Multilingual interview transcription","prompt":"I have a recorded interview in Spanish at https://example.com/entrevista.m4a — can you transcribe it to plain text? The language is Spanish (es)."}],"resultDescription":"Returns a JSON object with the full transcribed text, detected language code, total duration in seconds, and an array of segments each containing start time, end time, and text. If format=srt or format=vtt is requested, returns a ready-made subtitle file string instead. If format=text, returns plain text only.","failureModes":["File exceeds 80 MB or 5 minutes — likely returns an error or truncated result","Unsupported file format — endpoint may return an error for formats other than mp3, wav, m4a, mp4, webm, etc.","Unreachable URL — if the audio/video URL is not publicly accessible, transcription fails","Very noisy or silent audio — may produce empty or garbled text with no clear error","Invalid language code — may fall back to auto-detect or return an error","Payment not completed — x402 payment required; missing payment returns 402 response"],"whenToPreferThis":"Choose this endpoint when you need fast, affordable speech-to-text transcription from a public audio or video URL (up to 5 minutes / 80 MB), especially when you need timestamped segments or ready-made SRT/VTT subtitle files. It is ideal for podcast transcription, video captioning, meeting notes, and multilingual content (99 languages auto-detected). At $0.02 per call it is cost-effective for single-file transcription tasks.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-23T14:04:59.828Z","isFirstParty":false,"canonicalSlug":"sift-web-tools-speech-to-text-transcription-020bea2c"}