{"slug":"dicta-notes-com-routes-x402-transcribe-852bf0","title":"Transcribe short audio fast","host":"dicta-notes.com","method":"POST","resource":"https://dicta-notes.com/routes/x402/transcribe","category":"image","description":"Transcribe short audio fast: POST JSON with an audio_url (voicemail, call recording, voice memo, podcast clip — up to 15 min) and get Gemini-powered transcript JSON back with speaker-labeled, timestamped segments — any spoken language, auto-detected and labeled per segment. Handles mp3, wav, m4a, og","price_listed":0.1,"price_asked":0.1,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":346,"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://example.com/voicemail.mp3","store":false},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"audio_url":{"description":"Public http(s) URL of the audio file (up to 15 minutes, 100 MB max).","format":"uri","type":"string"},"store":{"description":"Optional. When true, encrypt and store the transcript JSON for 60 days.","type":"boolean"}},"required":["audio_url"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"duration_seconds":{"type":"number"},"language":{"type":"string"},"languages_detected":{"items":{"type":"string"},"type":"array"},"segments":{"items":{"properties":{"confidence":{"type":["number","null"]},"end_time":{"type":"number"},"language":{"type":"string"},"speaker":{"type":"string"},"start_time":{"type":"number"},"text":{"type":"string"}},"required":["speaker","text","start_time","end_time","language"],"type":"object"},"type":"array"},"speakers":{"items":{"type":"string"},"type":"array"},"transcript":{"type":"string"}},"required":["transcript","segments","speakers","duration_seconds","language","languages_detected"],"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-09-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.1,"price_match":true,"latency_ms":346,"error":null}],"description_full":"Transcribe short audio fast: POST JSON with an audio_url (voicemail, call recording, voice memo, podcast clip — up to 15 min) and get Gemini-powered transcript JSON back with speaker-labeled, timestamped segments — any spoken language, auto-detected and labeled per segment. Handles mp3, wav, m4a, ogg, webm, flac. $0.10 flat in USDC on Base — no account, no API key. For hour-long meetings use /routes/x402/transcribe-long.","last_updated":"2026-08-29T13:44:50.462Z","schemes":["exact"]}