{"slug":"agent-toolbox-zafermemon87-workers-dev-v1-transcribe-1e0069","title":"Speech to text with Whisper large v3 turbo","host":"agent-toolbox.zafermemon87.workers.dev","method":"POST","resource":"https://agent-toolbox.zafermemon87.workers.dev/v1/transcribe","category":"image","description":"Speech to text with Whisper large v3 turbo: transcribe audio (mp3, wav, m4a, ogg, webm; up to 20 MB, about 20 minutes) from a URL or base64, or translate the speech into English. Returns the text, language, duration and timed segments.","price_listed":0.01,"price_asked":0.01,"state":"answering","state_label":"Answering","checks_7d":2,"answered_7d":2,"latency_ms_median":37,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"audio_url":"https://example.com/meeting.mp3"},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"properties":{"audio_base64":{"description":"The audio file, base64-encoded","type":"string"},"audio_url":{"description":"A public http(s) URL","type":"string"},"language":{"description":"Language code such as en or hi (detected when left out)","type":"string"},"task":{"description":"translate = into English","enum":["transcribe","translate"],"type":"string"}},"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":{"type":"object"},"type":{"type":"string"}},"required":["type"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-10-25","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.01,"price_match":true,"latency_ms":34,"error":null},{"day":"2026-10-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.01,"price_match":true,"latency_ms":41,"error":null}],"description_full":"Speech to text with Whisper large v3 turbo: transcribe audio (mp3, wav, m4a, ogg, webm; up to 20 MB, about 20 minutes) from a URL or base64, or translate the speech into English. Returns the text, language, duration and timed segments.","last_updated":"2026-10-24T13:49:50.364Z","schemes":["exact"]}