{"uid":"cap_PuZ3-1GeQNYrZPKtTD0eV","slug":"x402-deployer-x402-deployer-workers-dev-78609d3a","name":"Speaker Diarization & Multi-Speaker Transcription","description":"Speaker diarization / who-said-what transcription. Whisper v3 + speaker labels. Returns utterances grouped by speaker, plus per-speaker stats (count, seconds, words). 60 min max.","url":"https://x402-deployer.x402-deployer.workers.dev/speaker-diarize","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"required":["media_url"],"properties":{"language":{"type":"string","description":"ISO language code hint for transcription. Optional; auto-detected if omitted."},"media_url":{"type":"string","description":"Audio or video URL to transcribe and diarize. Max 60 minutes duration."},"num_speakers":{"type":"number","description":"Expected number of speakers. Optional; 1-20, auto-detected if omitted."}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"utterances":{"type":"array","items":{"type":"object","properties":{"end":{"type":"number"},"text":{"type":"string"},"start":{"type":"integer"},"speaker":{"type":"string"}}}},"speaker_count":{"type":"integer"},"duration_seconds":{"type":"integer"}}}}}}},"responseSchema":null,"example":{"request":{"input":{"body":{"language":"en","media_url":"https://www.soundhelix.com/examples/mp3/SoundHelix-Song-1.mp3","num_speakers":2},"type":"http","method":"POST","bodyType":"json"}},"response":{"text":"♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪♪♪ ♪♪ ♪♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ Thank you.","source_url":"https://www.soundhelix.com/examples/mp3/SoundHelix-Song-1.mp3","utterances":[{"end":63.92,"text":"♪ ♪ ♪ ♪ ♪ ♪ ♪","start":0.02,"speaker":"Unknown"},{"end":131.06,"text":"♪♪♪ ♪♪ ♪♪","start":66.02,"speaker":"Unknown"},{"end":348.3,"text":"♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪ ♪","start":133.72,"speaker":"Unknown"},{"end":369.98,"text":"Thank you.","start":350.24,"speaker":"Unknown"}],"speaker_count":1,"speaker_stats":[{"speaker":"Unknown","word_count":27,"total_seconds":363.26,"utterance_count":4}],"duration_seconds":372.715083,"detected_languages":null}},"exampleRequest":{"language":"en","media_url":"https://www.soundhelix.com/examples/mp3/SoundHelix-Song-1.mp3","num_speakers":2},"tags":["x402"],"displayCostAmount":"0.1","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","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_k0kKczcv_8uaSjdcSDF2b","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 audio with speaker labels using Whisper v3, returning utterances grouped by speaker with per-speaker statistics (utterance count, total seconds, word count).","exampleAgentPrompt":"Transcribe this podcast audio and tell me who said what — I need the transcript broken out by speaker with stats on how much each person spoke: [audio URL].","exampleUseCases":null,"resultDescription":"A structured response containing utterances grouped by speaker with speaker labels, plus per-speaker statistics including utterance count, total duration in seconds, and word count for each identified speaker.","failureModes":["Unsupported audio format returns an error","Audio URL unreachable or times out","Single-speaker audio may produce inaccurate diarization","Very long audio files may exceed processing limits","Payment failure returns 402 with payment details","Overlapping speech may reduce speaker separation accuracy"],"whenToPreferThis":"Choose this endpoint when you need to know not just what was said but who said it — e.g. for interviews, meetings, podcasts, or multi-party calls. It combines Whisper v3 transcription quality with speaker separation, returning both the full labeled transcript and per-speaker usage statistics in one call. Prefer this over plain transcription endpoints when speaker attribution matters.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T06:38:13.737Z","isFirstParty":false}