{"slug":"medien-halowerk-com-v1-diarize-ce5468","title":"Takes an audio or video file by URL or inline base64 and reports who spoke when","host":"medien.halowerk.com","method":"POST","resource":"https://medien.halowerk.com/v1/diarize","category":"image","description":"Takes an audio or video file by URL or inline base64 and reports who spoke when. Every turn comes back with its speaker label, start and end time, duration, word count and text, and consecutive words from the same speaker are merged into one turn rather than left as a word list.","price_listed":0.025,"price_asked":0.025,"state":"answering","state_label":"Answering","checks_7d":1,"answered_7d":1,"latency_ms_median":1195,"reported_calls_30d":1,"reported_payers_30d":1,"networks":["eip155:8453"],"badge":"unverified","paid_checks_7d":0,"paid_ok_7d":0,"example_input":{"body":{"duration_minutes":1,"language":"en","source":{"url":"https://samplelib.com/lib/preview/mp3/sample-3s.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.","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.","maximum":30,"minimum":1,"type":"integer"},"include_turn_text":{"default":true,"description":"Include the text of each turn. Off returns only the timeline and the figures.","type":"boolean"},"language":{"description":"BCP-47 code such as de, en. \"multi\" enables multilingual recognition at the provider's higher rate. Omit to detect.","maxLength":12,"type":"string"},"source":{"additionalProperties":false,"description":"The recording. Either url or content_base64.","properties":{"content_base64":{"description":"The file inline, base64.","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":"2026-09-29","reachable":true,"status":402,"valid_402":true,"asked_usdc":0.025,"price_match":true,"latency_ms":1195,"error":null}],"description_full":"Takes an audio or video file by URL or inline base64 and reports who spoke when. Every turn comes back with its speaker label, start and end time, duration, word count and text, and consecutive words from the same speaker are merged into one turn rather than left as a word list.","last_updated":"2026-09-28T18:00:22.447Z","schemes":["exact"]}