{"info":{"title":"ModelRunner OpenAPI schema for openai/whisper","version":"0.1.0"},"paths":{"/health-check":{"get":{"summary":"Healthcheck","responses":{"200":{"content":{"application/json":{"schema":{"title":"Response Healthcheck Health Check Get"}}},"description":"Successful Response"}},"operationId":"healthcheck_health_check_get"}}},"openapi":"3.1.0","components":{"schemas":{"Input":{"type":"object","title":"Input","required":["audio_url"],"properties":{"task":{"allOf":[{"$ref":"#/components/schemas/TaskEnum"}],"title":"Task","default":"transcribe","x-order":1,"description":"Whether to transcribe the audio in its spoken language or translate it into English text."},"prompt":{"type":"string","title":"Prompt","default":"","x-order":6,"description":"Optional text hint to bias transcription toward specific terms or spelling."},"diarize":{"type":"boolean","title":"Diarize","default":false,"x-order":3,"description":"Annotate which speaker said each chunk. Adds processing time (and therefore cost)."},"language":{"anyOf":[{"$ref":"#/components/schemas/LanguageEnum"},{"type":"null"}],"title":"Language","default":null,"x-order":2,"description":"ISO code of the spoken language. Leave unset to auto-detect."},"audio_url":{"type":"string","title":"Audio URL","format":"uri","x-order":0,"description":"URL of the audio file to transcribe. Supported formats: mp3, mp4, mpeg, mpga, m4a, wav or webm."},"batch_size":{"type":"integer","title":"Batch Size","default":64,"maximum":64,"minimum":1,"x-order":5,"description":"Internal batch size for inference."},"chunk_level":{"allOf":[{"$ref":"#/components/schemas/ChunkLevelEnum"}],"title":"Chunk Level","default":"segment","x-order":4,"description":"Timestamp granularity: none, segment (default), or word."},"num_speakers":{"anyOf":[{"type":"integer","minimum":1},{"type":"null"}],"title":"Num Speakers","default":null,"x-order":7,"description":"Expected number of speakers. Only used when diarize is true; leave unset to auto-detect."}},"x-fal-order-properties":["audio_url","task","language","diarize","chunk_level","batch_size","prompt","num_speakers"]},"Output":{"type":"string","title":"Output","description":"The full transcribed text."},"TaskEnum":{"enum":["transcribe","translate"],"type":"string","title":"TaskEnum"},"LanguageEnum":{"enum":["af","am","ar","as","az","ba","be","bg","bn","bo","br","bs","ca","cs","cy","da","de","el","en","es","et","eu","fa","fi","fo","fr","gl","gu","ha","haw","he","hi","hr","ht","hu","hy","id","is","it","ja","jw","ka","kk","km","kn","ko","la","lb","ln","lo","lt","lv","mg","mi","mk","ml","mn","mr","ms","mt","my","ne","nl","nn","no","oc","pa","pl","ps","pt","ro","ru","sa","sd","si","sk","sl","sn","so","sq","sr","su","sv","sw","ta","te","tg","th","tk","tl","tr","tt","uk","ur","uz","vi","yi","yo","zh"],"type":"string","title":"LanguageEnum"},"ChunkLevelEnum":{"enum":["none","segment","word"],"type":"string","title":"ChunkLevelEnum"}}}}