{"uid":"cap_2h9e5dPIwPqLA9y8KnLeO","slug":"x402engine-audio-transcription-with-speaker-identification-3dd2487e","name":"x402engine Audio Transcription with Speaker Identification","description":"Convert audio to text with speaker identification — covers up to 10 minutes of audio","url":"https://x402engine.app/api/transcribe?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","bodyType","body","method"],"properties":{"body":{"type":"object","anyOf":[{"required":["audio_url"]},{"required":["audio_base64"]}],"properties":{"audio_url":{"type":"string","example":"https://example.com/audio.mp3","description":"URL of audio file to transcribe (provide audio_url OR audio_base64, not both)"},"audio_base64":{"type":"string","example":"data:audio/mp3;base64,SGVsbG8=","description":"Base64-encoded audio data with MIME type prefix (provide audio_url OR audio_base64, not both)"},"audio_mimetype":{"type":"string","example":"audio/mp3","description":"MIME type when using audio_base64 (e.g. audio/mp3, audio/wav)"}},"additionalProperties":false},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.1","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"registry","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"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_8jt2qvYdcD-Lc1IPEfcZA","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.1","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Transcribes up to 10 minutes of audio to text with speaker diarization, accepting either a URL or base64-encoded audio","exampleAgentPrompt":"Can you transcribe this meeting recording for me and tell me who said what? Here's the audio file URL: https://example.com/meeting.mp3","exampleUseCases":[{"title":"Meeting transcript with speaker attribution","prompt":"I have a recording of a client call at https://recordings.myco.com/call-2024-06-01.mp3 — can you transcribe it and label which parts were said by which speaker?"},{"title":"Podcast episode to text","prompt":"Transcribe this podcast episode from https://mypodcast.com/ep42.mp3 and identify the different speakers throughout the conversation."},{"title":"Voice note transcription from base64","prompt":"I've got a short voice memo encoded in base64 — it's audio/wav format. Can you transcribe it and tell me if there are multiple speakers?"}],"resultDescription":"Returns a full text transcript of the audio content, with speaker identification labels (e.g. Speaker 1, Speaker 2) annotating which segments each speaker was responsible for. Covers recordings up to 10 minutes in length.","failureModes":["Audio file exceeds 10-minute limit — request rejected or truncated","Invalid or inaccessible audio URL — returns network or fetch error","Malformed base64 data or missing MIME type prefix — returns parsing error","Unsupported audio format — returns format error","Both audio_url and audio_base64 provided simultaneously — schema validation error","Neither audio_url nor audio_base64 provided — returns missing field error"],"whenToPreferThis":"Choose this endpoint when you need automatic speech-to-text transcription combined with speaker diarization (who said what) in a single pay-per-call API call, especially for recordings up to 10 minutes. Prefer this over generic transcription APIs when you want speaker labels without setting up your own diarization pipeline, and when paying per use via USDC micropayments (x402 protocol) is acceptable.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-11-11T15:43:41.780Z","isFirstParty":false,"canonicalSlug":"x402engine-audio-transcription-with-speaker-identification-3dd2487e"}