{"slug":"x402-ochinimus-app-api-transcribe-ca6e77","title":"Speech to text","host":"x402.ochinimus.app","method":"GET","resource":"https://x402.ochinimus.app/api/transcribe","category":"image","description":"Speech to text: the text, timed segments and the spoken language for mp3, wav, m4a, ogg or webm audio (10 MB, 5 minutes, checked from the file). Use when you need to answer: What is said in this audio file? Cached 24 hours by the audio itself.","price_listed":0.01,"price_asked":0.01,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":898,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["algorand:wGHE2Pwdvd7S12BL5FaOP20EGYesN73ktiC1qzkkit8=","eip155:137","eip155:42161","eip155:5042","eip155:8453","solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"method":"GET","queryParams":{"url":"https://www.w3schools.com/html/horse.mp3"},"type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"method":{"enum":["GET"],"type":"string"},"queryParams":{"properties":{"url":{"description":"the audio file: an absolute http or https URL","type":"string"}},"required":["url"],"type":"object"},"type":{"const":"http","type":"string"}},"required":["type","method"],"type":"object"},"output":{"properties":{"example":{"properties":{"data":{"properties":{"audio":{"type":"object"},"cached":{"type":"boolean"},"fetched_at":{"type":"string"},"final_url":{"type":"string"},"language":{"type":"string"},"model":{"type":"string"},"no_speech_found":{"type":"boolean"},"segments":{"type":"array"},"source_url":{"type":"string"},"text":{"type":"string"}},"type":"object"},"paid":{"type":"boolean"},"tool":{"type":"string"}},"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-18","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.01,"price_match":true,"latency_ms":898,"error":null}],"description_full":"Speech to text: the text, timed segments and the spoken language for mp3, wav, m4a, ogg or webm audio (10 MB, 5 minutes, checked from the file). Use when you need to answer: What is said in this audio file? Cached 24 hours by the audio itself.","last_updated":"2026-10-14T06:46:58.263Z","schemes":["batch-settlement","exact"]}