{"name":"speaker-diarize","description":"Transcribe audio or video and label who said what. Send a media_url (optionally language and num_speakers) and it runs Whisper v3 speech-to-text with speaker diarization, returning an utterances array grouped by speaker with start/end timestamps and text, plus per-speaker stats (utterance count, seconds spoken, word count) and total duration_seconds. Files up to 60 minutes are supported. Use it as a speaker diarization API, who-said-what transcription tool, multi-speaker transcript generator, or meeting/interview transcription service for calls, podcasts, and recorded interviews.","price":"$0.10","method":"POST","input_schema":{"properties":{"media_url":{"type":"string","description":"Audio or video URL to transcribe and diarize. Max 60 minutes duration."},"language":{"type":"string","description":"ISO language code hint for transcription. Optional; auto-detected if omitted."},"num_speakers":{"type":"number","description":"Expected number of speakers. Optional; 1-20, auto-detected if omitted."}},"required":["media_url"]},"input_example":{"media_url":"https://download.samplelib.com/mp3/sample-3s.mp3"},"output_example":{"utterances":[{"speaker":"Speaker 0","start":0,"end":5.2,"text":"Hello"}],"speaker_count":2,"duration_seconds":600},"x402_payment_required":true,"x402_facilitator":"https://api.cdp.coinbase.com/platform/v2/x402"}