{"uid":"cap_hv5xw0xrXtnE1Yk0k_3V6","slug":"dicta-notes-short-audio-transcription-5d83bcae","name":"Dicta Notes Short Audio Transcription","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, ogg, webm, flac. $0.10 flat in USDC on Base — no account, no API key. For hour-long meetings use /routes/x402/transcribe-long.","url":"https://dicta-notes.com/routes/x402/transcribe?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"store":{"type":"boolean","description":"Optional. When true, encrypt and store the transcript JSON for 60 days."},"audio_url":{"type":"string","format":"uri","description":"Public http(s) URL of the audio file (up to 15 minutes, 100 MB max)."}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.1","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":{"p10Cents":"10.0000","medianCents":"10.0000","p90Cents":"10.0000","minCents":"10.0000","maxCents":"10.0000","p95Cents":"10.0000","sampleCount":1,"varies":false,"failureChargeRate":1},"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.1/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.1","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.1","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_D9lU3WMuE8-GOpvIVlAJs","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.1","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes audio files up to 15 minutes into speaker-labeled, timestamped, multilingual transcript segments using Gemini AI","exampleAgentPrompt":"Can you transcribe this voicemail recording for me — here's the URL: https://example.com/voicemail.mp3 — and tell me who said what with timestamps?","exampleUseCases":[{"title":"Voicemail transcription for CRM logging","prompt":"I just got a voicemail from a customer at https://storage.example.com/voicemail-john-doe.mp3 — can you transcribe it with speaker labels and timestamps so I can log it in our CRM?"},{"title":"Multilingual call recording review","prompt":"We recorded a support call at https://cdn.example.com/support-call-2024.wav that might switch between English and Spanish — please transcribe it with each speaker identified and language labeled per segment."},{"title":"Podcast clip show notes","prompt":"I have a 10-minute podcast clip at https://media.example.com/episode42-clip.mp3 and need a full transcript with speaker names and timestamps so I can write show notes from it."}],"resultDescription":"Returns a JSON object with a full transcript string, an array of segments each containing speaker label, text, start_time, end_time, language, and optional confidence score; plus a speakers array, total duration_seconds, primary language, and all languages_detected in the audio.","failureModes":["Audio URL not publicly accessible — returns error if file requires authentication or is behind a firewall","File exceeds 15 minutes or 100 MB limit — should use the long-form /transcribe-long endpoint instead","Unsupported audio format — only mp3, wav, m4a, ogg, webm, flac are supported","Payment failure — USDC transaction on Base not confirmed","Audio too noisy or low quality — transcript may have gaps or low confidence scores","URL is malformed or audio file is corrupted — returns processing error"],"whenToPreferThis":"Choose this endpoint when you need fast, speaker-labeled, timestamped transcription of audio files up to 15 minutes without requiring an account or API key. It is ideal for voicemails, short call recordings, voice memos, and podcast clips in any spoken language. For recordings over 15 minutes (up to 2 hours), use the sibling /transcribe-long endpoint instead.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T06:34:43.337Z","isFirstParty":false,"canonicalSlug":"dicta-notes-short-audio-transcription-5d83bcae"}