{"id":"elevenlabs/scribe-v2","object":"model","type":"model","name":"Scribe v2","creator":"ElevenLabs","modality":"text","tasks":["speech-to-text","captions"],"description":"ElevenLabs' most accurate transcription: word timings, speaker labels and 90+ languages, from a sound or a video. Billed per started minute of the recording.","revision":"2026-10-03","version":null,"latest":true,"status":"stable","deprecation":null,"pricing":{"unit":"minute","usd":"0.011","overrides":[],"drivers":["audio_file","video"],"length_of":["audio_file","video"],"length_step":60},"input_schema":{"type":"object","additionalProperties":false,"properties":{"audio_file":{"type":"string","title":"Recording","pattern":"^file_[0-9A-Za-z]{24}$","x-leap-ui":{"group":"main","order":3,"widget":"audio","help":"The sound to transcribe: an uploaded file, by ID. Up to 4 hours."}},"video":{"type":"string","title":"Video","pattern":"^file_[0-9A-Za-z]{24}$","x-leap-ui":{"group":"main","order":4,"widget":"video","help":"Or a video whose speech to transcribe: an uploaded file, by ID. Up to 4 hours."}},"language":{"type":"string","title":"Language","oneOf":[{"const":"auto","title":"Detect"},{"const":"en","title":"English"},{"const":"es","title":"Spanish"},{"const":"pt","title":"Portuguese"},{"const":"fr","title":"French"},{"const":"de","title":"German"},{"const":"it","title":"Italian"},{"const":"nl","title":"Dutch"},{"const":"pl","title":"Polish"},{"const":"ru","title":"Russian"},{"const":"uk","title":"Ukrainian"},{"const":"tr","title":"Turkish"},{"const":"ar","title":"Arabic"},{"const":"he","title":"Hebrew"},{"const":"fa","title":"Persian"},{"const":"hi","title":"Hindi"},{"const":"bn","title":"Bengali"},{"const":"ur","title":"Urdu"},{"const":"ta","title":"Tamil"},{"const":"id","title":"Indonesian"},{"const":"ms","title":"Malay"},{"const":"tl","title":"Filipino"},{"const":"vi","title":"Vietnamese"},{"const":"th","title":"Thai"},{"const":"zh","title":"Chinese"},{"const":"ja","title":"Japanese"},{"const":"ko","title":"Korean"},{"const":"sv","title":"Swedish"},{"const":"da","title":"Danish"},{"const":"no","title":"Norwegian"},{"const":"fi","title":"Finnish"},{"const":"el","title":"Greek"},{"const":"cs","title":"Czech"},{"const":"ro","title":"Romanian"},{"const":"hu","title":"Hungarian"},{"const":"sw","title":"Swahili"},{"const":"yo","title":"Yoruba"}],"default":"auto","x-leap-ui":{"group":"main","order":6,"widget":"select","help":"The language spoken. Detect works for most recordings."}},"speakers":{"type":"boolean","title":"Speaker labels","default":true,"x-leap-ui":{"group":"main","order":7,"widget":"toggle","help":"Tell the voices apart: Speaker 1, Speaker 2."}},"settings":{"type":"object","title":"Model settings","additionalProperties":false,"default":{},"properties":{"sound_events":{"type":"boolean","title":"Sound tags","default":false,"x-leap-ui":{"group":"advanced","order":30,"widget":"toggle","help":"Mark laughter, applause and music in the transcript."}}}}},"allOf":[{"description":"Send one recording: a sound or a video, not both.","not":{"type":"object","properties":{"audio_file":{"type":"string","pattern":"^file_[0-9A-Za-z]{24}$"},"video":{"type":"string","pattern":"^file_[0-9A-Za-z]{24}$"}},"required":["audio_file","video"]}},{"description":"Add the recording to transcribe: a sound or a video.","if":{"type":"object","not":{"type":"object","properties":{"video":{"type":"string","pattern":"^file_[0-9A-Za-z]{24}$"}},"required":["video"]}},"then":{"type":"object","properties":{"audio_file":{"type":"string","pattern":"^file_[0-9A-Za-z]{24}$"}},"required":["audio_file"]}}]}}