{"slug":"x402-gateway-blackwoodstate8-workers-dev-v1-speech-to-text-847c5f","title":"Use when you need speech to text transcription or translation of an audio file a","host":"x402-gateway.blackwoodstate8.workers.dev","method":"POST","resource":"https://x402-gateway.blackwoodstate8.workers.dev/v1/speech-to-text","category":"image","description":"Use when you need speech to text transcription or translation of an audio file at a public URL. Do not use for audio over 10 MB or speaker labels. Returns JSON with a Whisper transcription of an audio file: text, timed segments and language, or an English translation for 0.005 USDC per megabyte, up ","price_listed":0.05,"price_asked":0.05,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":1180,"reported_calls_30d":5,"reported_payers_30d":1,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"url":"https://upload.wikimedia.org/wikipedia/commons/b/bb/Neil_Armstrong_small_step.wav"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"language":{"description":"ISO 639-1 code of the spoken language, e.g. en or pt (detected when omitted)","pattern":"^[a-z]{2}$","type":"string"},"task":{"description":"transcribe keeps the spoken language; translate returns English (transcribe when omitted)","enum":["transcribe","translate"],"type":"string"},"url":{"description":"Public http(s) URL of the audio file, e.g. https://example.com/talk.mp3 (mp3, wav, ogg, m4a, webm; up to 10 MB)","format":"uri","maxLength":2048,"type":"string"}},"required":["url"],"type":"object"},"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":{"additionalProperties":false,"properties":{"expiresAt":{"description":"ISO 8601: depois disso o resultado deixa de existir","type":"string"},"jobId":{"maxLength":100,"minLength":1,"type":"string"},"next":{"additionalProperties":false,"description":"Suggested next paid call in the same family (call it in a loop when the task continues)","properties":{"method":{"enum":["GET","POST"],"type":"string"},"sample":{"description":"Free fixed sample of the whole family","type":"string"},"service":{"description":"Service id of the suggested next paid call","type":"string"},"tool":{"description":"MCP tool name of the same call","type":"string"},"url":{"description":"Paid route of the next call","type":"string"},"useWhen":{"description":"When the next call is the right one","type":"string"}},"required":["service","tool","method","url","useWhen","sample"],"type":"object"},"pollUrl":{"format":"uri","type":"string"},"status":{"const":"queued","type":"string"}},"required":["jobId","pollUrl","expiresAt","status"],"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":0.05,"price_match":true,"latency_ms":1180,"error":null}],"description_full":"Use when you need speech to text transcription or translation of an audio file at a public URL. Do not use for audio over 10 MB or speaker labels. Returns JSON with a Whisper transcription of an audio file: text, timed segments and language, or an English translation for 0.005 USDC per megabyte, up to 0.05 USDC per call (clients without upto pay the cap). Asynchronous: the paid call returns a jobId and a free pollUrl; typical job time 20000 ms (p95). Category: Media.","last_updated":"2026-10-18T11:37:31.498Z","schemes":["exact","upto"]}