{"uid":"cap_Xf2jBDl3pue0O85IGTtTk","slug":"transcribe-by-youraitools-b8b7517e","name":"Transcribe by YourAITools","description":"Speech-to-text API (audio transcription) for AI agents. Send MP3 or WAV (body, audio_url or base64, up to 30 min); get transcript, language, timestamped segments, optional SRT/VTT; task=translate gives English. $0.003 per audio minute, rounded up; the 402 quotes your file's exact total. Search intents: speech to text api, transcribe audio file, mp3 to text, wav to text, whisper api pay per minute, srt vtt subtitles, podcast transcription.","url":"https://api.youraitools.co/transcribe/v1/transcribe?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$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","required":["audio_url"],"properties":{"vad":{"type":"boolean","description":"Skip silence with voice activity detection (default false)"},"task":{"enum":["transcribe","translate"],"type":"string","description":"transcribe (default) or translate (to English)"},"format":{"enum":["json","srt","vtt"],"type":"string","description":"json (default); srt or vtt also returns subtitles in the srt / vtt field"},"prompt":{"type":"string","description":"Optional context words or spellings (max 500 chars)"},"language":{"type":"string","description":"Optional ISO 639-1 code of the spoken language (e.g. en, es, de); detected when omitted"},"audio_url":{"type":"string","description":"Public https URL of an MP3 or WAV file (up to 30 minutes / 30 MB). Or POST the file as the raw body (Content-Type audio/mpeg or audio/wav), or JSON audio_base64."}},"description":"Search intents: speech to text api, transcribe audio file, mp3 to text, wav to text, pay per minute transcription api, srt vtt subtitles, podcast transcription"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"srt":{"type":["string","null"]},"vtt":{"type":["string","null"]},"text":{"type":"string"},"language":{"type":["string","null"]},"segments":{"type":"array","items":{"type":"object","properties":{"end":{"type":"number"},"text":{"type":"string"},"start":{"type":"number"}}}},"total_usd":{"type":"string"},"billed_minutes":{"type":"integer"},"duration_seconds":{"type":"number"}}}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","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":"$0.003/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_8OaLcZtDzWXu58vz98H2D","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Converts MP3 or WAV audio files to text transcripts with timestamped segments, language detection, and optional SRT/VTT subtitle output via pay-per-minute pricing.","exampleAgentPrompt":"Can you transcribe this podcast episode for me? Here's the MP3 URL: https://example.com/episode42.mp3 — I'd like the output in SRT format so I can use it as subtitles, and please detect the language automatically.","exampleUseCases":[{"title":"Podcast episode subtitles","prompt":"I have a 20-minute podcast episode at https://mypodcast.com/ep10.mp3 — can you transcribe it and give me the subtitles as an SRT file so I can upload them to YouTube?"},{"title":"Multilingual interview transcription","prompt":"Please transcribe this Spanish-language interview audio at https://media.example.com/interview.wav — detect the language automatically and give me the full transcript with timestamps for each segment."},{"title":"Translate foreign audio to English","prompt":"I've got an audio file of a German conference talk at https://conference.example.com/talk.mp3 — can you translate it to English text so I can read what was said?"}],"resultDescription":"Returns a JSON object containing the full transcript text, detected language code, an array of timestamped segments (each with start time, end time, and text), billed minutes, duration in seconds, and total cost in USD. If SRT or VTT format was requested, includes the formatted subtitle string in the corresponding field.","failureModes":["Audio URL is not publicly accessible or returns a non-200 status — endpoint cannot fetch the file","File exceeds 30-minute or 30 MB limit — request rejected","Unsupported audio format supplied — only MP3 and WAV are accepted","402 Payment Required returned when credits are exhausted — response body quotes exact cost for the file","Language code is invalid ISO 639-1 — may fall back to auto-detection or error","Network timeout for very large files hosted on slow servers"],"whenToPreferThis":"Choose this endpoint when you need pay-per-minute audio transcription with timestamped segments and optional subtitle output (SRT/VTT) without a monthly subscription. It is ideal for agents that process variable volumes of audio on demand, need language auto-detection, or require English translation of non-English audio. Prefer it over flat-rate APIs when call frequency is low or file sizes vary widely, since billing is rounded up per minute at $0.003/min.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-27T15:29:37.085Z","isFirstParty":false,"canonicalSlug":"transcribe-by-youraitools-b8b7517e"}