{"slug":"voice-madebydevx-com-v1-stt-f82323","title":"Speech to text for agents","host":"voice.madebydevx.com","method":"POST","resource":"https://voice.madebydevx.com/v1/stt","category":"image","description":"Speech to text for agents: send an audio URL, base64 or raw audio (WAV, MP3, FLAC, OGG, M4A, WebM; up to 20 min / 10 MB) and get the transcript, language, timed segments and WebVTT subtitles. Optional task=translate gives English text. $0.002 USDC per started minute on Base; failed or silent audio i","price_listed":0.002,"price_asked":null,"state":"effects","state_label":"Not tested: has real-world effects","checks_7d":0,"answered_7d":0,"latency_ms_median":null,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"audio_url":"https://voice.madebydevx.com/samples/hello.mp3","language":"en"},"bodyType":"json","discoverable":true,"method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"additionalProperties":false,"properties":{"audio_base64":{"description":"Base64 audio (max 6 MB decoded); a data: URI prefix is allowed","type":"string"},"audio_url":{"description":"Public http(s) URL of the audio file (max 10 MB, 20 min)","type":"string"},"language":{"description":"ISO 639-1 code like \"en\", or \"auto\" (default) to detect","type":"string"},"prompt":{"description":"Optional context words/spelling hints","maxLength":500,"type":"string"},"requestKey":{"description":"Optional idempotency key: the same payer + requestKey + input within 7 days returns the stored result without a second charge.","maxLength":128,"minLength":8,"pattern":"^[A-Za-z0-9][A-Za-z0-9._:-]{7,127}$","type":"string"},"task":{"description":"translate = English output","enum":["transcribe","translate"],"type":"string"},"vad":{"description":"Voice activity detection pre-filter","type":"boolean"}},"type":"object"},"bodyType":{"enum":["json"],"type":"string"},"discoverable":{"type":"boolean"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"operation_id":{"type":"string"},"payment":{"type":"object"},"result":{"type":"object"},"status":{"type":"string"}},"required":["operation_id","status","result"],"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[],"description_full":"Speech to text for agents: send an audio URL, base64 or raw audio (WAV, MP3, FLAC, OGG, M4A, WebM; up to 20 min / 10 MB) and get the transcript, language, timed segments and WebVTT subtitles. Optional task=translate gives English text. $0.002 USDC per started minute on Base; failed or silent audio is not charged. Whisper large-v3-turbo. By DevX.","last_updated":"2026-10-22T14:43:04.018Z","schemes":["exact"]}