{"slug":"medien-halowerk-com-v1-stt-ccd065","title":"Takes an audio or video file by URL or inline base64 and returns the transcript","host":"medien.halowerk.com","method":"POST","resource":"https://medien.halowerk.com/v1/stt","category":"image","description":"Takes an audio or video file by URL or inline base64 and returns the transcript: the full text, every word with start and end time and its own confidence, the utterances and paragraphs the recogniser separated, and the detected language with its confidence where no language was specified.","price_listed":0.06,"price_asked":0.06,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":1180,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"confidence_threshold":0.7,"duration_minutes":3,"language":"de","source":{"url":"https://example.com/besprechung.mp3"}},"bodyType":"json","method":"POST","type":"http"},"output_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","properties":{"input":{"additionalProperties":false,"properties":{"body":{"additionalProperties":false,"properties":{"confidence_threshold":{"default":0.7,"description":"Words below this confidence are listed separately as the passages worth checking.","maximum":1,"minimum":0,"type":"number"},"duration_minutes":{"description":"Length of the recording in started minutes — this is what you are billed for. A longer file is refused with its real length and nothing is charged; a shorter one costs what you declared, and the answer says how much less it would have been.","maximum":30,"minimum":1,"type":"integer"},"include_words":{"default":true,"description":"Return every word with its timestamp. Off returns only the text, paragraphs and utterances.","type":"boolean"},"language":{"description":"BCP-47 code such as de, en, es. \"multi\" enables multilingual recognition and is billed at the provider's higher rate. Omit to let the recogniser detect the language.","maxLength":12,"type":"string"},"source":{"additionalProperties":false,"description":"The recording. Either url or content_base64.","properties":{"content_base64":{"description":"The file inline, base64. Larger files must come by url.","maxLength":12000000,"type":"string"},"filename":{"maxLength":260,"type":"string"},"url":{"description":"Public http(s) URL of the audio or video file.","maxLength":2048,"type":"string"}},"type":"object"}},"required":["source","duration_minutes"],"type":"object"},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"type":{"const":"http","type":"string"}},"required":["type","method","bodyType","body"],"type":"object"}},"required":["input"],"type":"object"},"history":[{"day":"2026-09-24","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.06,"price_match":true,"latency_ms":1180,"error":null}],"description_full":"Takes an audio or video file by URL or inline base64 and returns the transcript: the full text, every word with start and end time and its own confidence, the utterances and paragraphs the recogniser separated, and the detected language with its confidence where no language was specified.","last_updated":"2026-09-21T09:57:49.979Z","schemes":["exact"]}