{"name":"video-to-text","description":"Video transcription / video to audio transcription / video to text / transcribe video / video speech-to-text / video ASR. Whisper v3 large transcription for any video URL — extracts audio internally. Auto-detects 90+ languages. Translate-to-English mode. 60-min / 500MB max. Speaker diarization optional.","price":"$0.10","method":"POST","input_schema":{"properties":{"media_url":{"type":"string"},"language":{"type":"string"},"task":{"type":"string","enum":["transcribe","translate"]},"diarize":{"type":"boolean"}},"required":["media_url"]},"input_example":{"media_url":"https://samplelib.com/mp4/sample-5s.mp4"},"output_example":{"text":"Hello world.","duration_seconds":23,"task":"transcribe"},"x402_payment_required":true,"x402_facilitator":"https://api.cdp.coinbase.com/platform/v2/x402"}