{"slug":"sift-srv1996466-hstgr-cloud-v1-transcribe-2ae920","title":"Speech to text from an audio or video file URL (up to 5 minutes), with timestamp","host":"sift.srv1996466.hstgr.cloud","method":"GET","resource":"https://sift.srv1996466.hstgr.cloud/v1/transcribe","category":"image","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","price_listed":0.02,"price_asked":0.02,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":817,"reported_calls_30d":2,"reported_payers_30d":2,"networks":["eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"method":"GET","queryParams":{"url":"https://sift.srv1996466.hstgr.cloud/samples/speech.mp3"},"type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"method":{"enum":["GET","HEAD","DELETE"],"type":"string"},"queryParams":{"properties":{"format":{"description":"json, text, srt or vtt (default json)","type":"string"},"language":{"description":"Two-letter language code, e.g. en (default auto-detect)","type":"string"},"url":{"description":"Audio or video file URL","type":"string"}},"required":["url"],"type":"object"},"type":{"const":"http","type":"string"}},"required":["type","method"],"type":"object"},"output":{"properties":{"example":{"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-20","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.02,"price_match":true,"latency_ms":817,"error":null}],"description_full":"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.","last_updated":"2026-10-19T21:30:12.765Z","schemes":["exact"]}