{"version":"1","model":{"id":"fal-ai/whisper","name":"Whisper (Transcribe)","kind":"audio","availability":"available","available":true,"restricted":false,"api_key_only":false,"description":"OpenAI Whisper large-v3 for high-accuracy transcription and translation across 99 languages with speaker diarization.","pricing_note":"~$0.006 / min","categories":["transcribe"],"prompt_required":false,"prompt_supported":true,"supports":{"referenceAudio":true},"requires":{"referenceAudio":true},"aspect_ratios":[],"resolutions":[],"durations":[],"base_credits":1,"api_gross_margin_percent":20,"added_at":"2026-05-05","popularity_rank":37,"preview":{"image":"/images/model-previews/generated/whisper-transcribe-v1.webp"},"schema_url":"/api/v1/models?id=fal-ai%2Fwhisper","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","$id":"https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fwhisper","title":"Whisper (Transcribe) generation request","description":"Request body accepted by POST /api/v1/generate for fal-ai/whisper.","type":"object","properties":{"model_id":{"type":"string","const":"fal-ai/whisper","description":"ArtEmotion model identifier."},"extra":{"type":"object","additionalProperties":true,"description":"Model-specific settings may also be nested here."},"max_credits":{"type":"number","minimum":1,"description":"Reject before submission if the estimated list price exceeds this cap."},"webhook_url":{"type":"string","format":"uri","maxLength":2048},"webhook_secret":{"type":"string","maxLength":512},"folder_id":{"type":"string"},"prompt":{"type":"string"},"batch_size":{"title":"Batch Size","description":"Number of parallel audio chunks processed at once. Higher values are faster but use more memory.","default":64,"type":"number","minimum":1,"maximum":64,"multipleOf":1},"diarize":{"title":"Diarize","description":"Whether to diarize the audio file. Defaults to false. Setting to true will add costs proportional to diarization inference time.","default":false,"type":"boolean"},"num_speakers":{"title":"Num Speakers","description":"Number of speakers in the audio file. Defaults to null. If not provided, the number of speakers will be automatically detected.","type":"number","minimum":1,"multipleOf":1},"chunk_level":{"title":"Chunk Level","description":"Level of the chunks to return. Either none, segment or word.","default":"segment","type":"string","enum":["none","segment","word"]},"task":{"title":"Task","description":"Task to perform on the audio file. Either transcribe or translate.","default":"transcribe","type":"string","enum":["transcribe","translate"]},"language":{"title":"Language","description":"Language of the audio file. Leave on Auto-detect unless you know the source language.","default":"","type":"string","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"]},"audio_url":{"type":"string","format":"uri"}},"required":["model_id","audio_url"],"additionalProperties":false},"parameters":[{"key":"batch_size","label":"Batch Size","type":"number","default":64,"min":1,"max":64,"step":1,"description":"Number of parallel audio chunks processed at once. Higher values are faster but use more memory."},{"key":"diarize","label":"Diarize","type":"toggle","default":false,"description":"Whether to diarize the audio file. Defaults to false. Setting to true will add costs proportional to diarization inference time."},{"key":"num_speakers","label":"Num Speakers","type":"number","min":1,"step":1,"description":"Number of speakers in the audio file. Defaults to null. If not provided, the number of speakers will be automatically detected."},{"key":"chunk_level","label":"Chunk Level","type":"select","default":"segment","options":["none","segment","word"],"description":"Level of the chunks to return. Either none, segment or word."},{"key":"task","label":"Task","type":"select","default":"transcribe","options":["transcribe","translate"],"description":"Task to perform on the audio file. Either transcribe or translate."},{"key":"language","label":"Language","type":"select","default":"","options":["","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"],"description":"Language of the audio file. Leave on Auto-detect unless you know the source language."}]}}