{"slug":"x402-agentutility-ai-video-transcribe-916515","title":"Transcribes any video URL to text with Whisper v3 large","host":"x402.agentutility.ai","method":"POST","resource":"https://x402.agentutility.ai/video-transcribe","category":"image","description":"Transcribes any video URL to text with Whisper v3 large. Auto-detects 90+ languages and offers a translate-to-English mode. 60-min / 500MB max. Same backend as video-to-text under a clearer slug. Use it for video transcription, video to audio transcription, or video-to-text. For speaker labels, use ","price_listed":0.1,"price_asked":0.1,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":3193,"reported_calls_30d":32,"reported_payers_30d":3,"networks":["eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"media_url":"https://samplelib.com/mp4/sample-5s.mp4"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"language":{"description":"Source language hint (ISO code). Optional; auto-detected if omitted.","type":"string"},"media_url":{"description":"URL of the video or audio file to transcribe. Max 60 minutes / 500MB.","type":"string"},"task":{"description":"'transcribe' (default) keeps original language, or 'translate' to English.","enum":["transcribe","translate"],"type":"string"}},"required":["media_url"]},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"},"output":{"properties":{"example":{"properties":{"duration_seconds":{"type":"integer"},"task":{"type":"string"},"text":{"type":"string"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-09-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.1,"price_match":true,"latency_ms":3193,"error":null}],"description_full":"Transcribes any video URL to text with Whisper v3 large. Auto-detects 90+ languages and offers a translate-to-English mode. 60-min / 500MB max. Same backend as video-to-text under a clearer slug. Use it for video transcription, video to audio transcription, or video-to-text. For speaker labels, use the speaker-diarize endpoint.","last_updated":"2026-09-16T15:05:23.54Z","schemes":["exact"]}