{"slug":"verifylite-hydratinghealingtouch-workers-dev-transcribe-9c206a","title":"Speech-to-text for one audio or video file by URL, using Whisper (turbo) on a GP","host":"verifylite.hydratinghealingtouch.workers.dev","method":"POST","resource":"https://verifylite.hydratinghealingtouch.workers.dev/transcribe","category":"image","description":"Speech-to-text for one audio or video file by URL, using Whisper (turbo) on a GPU. Returns the full transcript, timed segments, ready-made SRT and WebVTT captions, and the detected language; optional translation to English. Files up to 25 MB (about 25 minutes of typical MP3). Useful for captioning v","price_listed":0.05,"price_asked":0.05,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":39,"reported_calls_30d":0,"reported_payers_30d":0,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"url":"https://github.com/runpod-workers/sample-inputs/raw/main/audio/gettysburg.wav"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"additionalProperties":false,"properties":{"language":{"description":"Optional language code, e.g. 'en'. Detected automatically if omitted.","type":"string"},"translate":{"description":"Also translate the speech to English. Default false.","type":"boolean"},"url":{"description":"Absolute HTTP or HTTPS URL of an audio or video file, up to 25 MB.","type":"string"}},"required":["url"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"durationSeconds":{"type":["number","null"]},"language":{"type":["string","null"]},"model":{"type":"string"},"segments":{"items":{"type":"object"},"type":"array"},"srt":{"type":"string"},"text":{"type":"string"},"tool":{"type":"string"},"translation":{"type":"string"},"vtt":{"type":"string"}},"required":["tool","text","srt","vtt","segments"],"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-21","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.05,"price_match":true,"latency_ms":39,"error":null}],"description_full":"Speech-to-text for one audio or video file by URL, using Whisper (turbo) on a GPU. Returns the full transcript, timed segments, ready-made SRT and WebVTT captions, and the detected language; optional translation to English. Files up to 25 MB (about 25 minutes of typical MP3). Useful for captioning videos, indexing podcasts, or reading meetings. Not charged if the file can't be fetched or transcribed.","last_updated":"2026-10-21T15:07:21.63Z","schemes":["exact"]}