{"version":"1","model":{"id":"fal-ai/elevenlabs/speech-to-text/scribe-v2","name":"ElevenLabs Scribe v2","kind":"audio","availability":"available","available":true,"restricted":false,"api_key_only":false,"description":"ElevenLabs' Scribe v2 transcription model with key term biasing for improved accuracy on domain-specific vocabulary.","pricing_note":"$0.22 / hour; keyterm prompting adds $0.05 / hour (ElevenLabs direct)","categories":["transcribe"],"prompt_required":false,"prompt_supported":false,"supports":{"referenceAudio":true},"requires":{"referenceAudio":true},"aspect_ratios":[],"resolutions":[],"durations":[],"base_credits":1,"api_gross_margin_percent":20,"added_at":"2026-05-24","popularity_rank":17,"preview":{"image":"/images/model-previews/generated/elevenlabs-scribe-v2-v1.webp"},"schema_url":"/api/v1/models?id=fal-ai%2Felevenlabs%2Fspeech-to-text%2Fscribe-v2","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","$id":"https://www.artemotion.ai/api/v1/models?id=fal-ai%2Felevenlabs%2Fspeech-to-text%2Fscribe-v2","title":"ElevenLabs Scribe v2 generation request","description":"Request body accepted by POST /api/v1/generate for fal-ai/elevenlabs/speech-to-text/scribe-v2.","type":"object","properties":{"model_id":{"type":"string","const":"fal-ai/elevenlabs/speech-to-text/scribe-v2","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"},"language_code":{"title":"Language","description":"Language of the audio. Auto-detect works well for most clips.","default":"","type":"string","enum":["","eng","spa","fra","deu","por","ita","hin","zho","jpn","kor","ara","rus","ind","nld","tur","pol","swe","fil","msa","ron","ukr","ell","ces","dan","fin","bul","hrv","slk","tam","vie","tha","heb","hun","nor","cat"]},"diarize":{"title":"Diarize","description":"Annotate which speaker is talking at each point.","default":false,"type":"boolean"},"tag_audio_events":{"title":"Tag Audio Events","description":"Tag non-speech sounds like laughter, applause, or music.","default":true,"type":"boolean"},"keyterms":{"title":"Key Terms","description":"Vocabulary hints; each term is at most 5 words. Adds a surcharge to transcription, included by /api/v1/estimate.","type":"array","maxItems":1000,"items":{"type":"string","minLength":1,"maxLength":50}},"audio_url":{"type":"string","format":"uri"},"duration":{"type":"number","minimum":1,"maximum":7200,"default":60,"description":"Estimate-only fallback when no media is supplied. Generation measures source bytes before reserving credits; client duration cannot lower the bill."}},"required":["model_id","audio_url"],"additionalProperties":false},"parameters":[{"key":"language_code","label":"Language","type":"select","default":"","options":["","eng","spa","fra","deu","por","ita","hin","zho","jpn","kor","ara","rus","ind","nld","tur","pol","swe","fil","msa","ron","ukr","ell","ces","dan","fin","bul","hrv","slk","tam","vie","tha","heb","hun","nor","cat"],"description":"Language of the audio. Auto-detect works well for most clips."},{"key":"diarize","label":"Diarize","type":"toggle","default":false,"description":"Annotate which speaker is talking at each point."},{"key":"tag_audio_events","label":"Tag Audio Events","type":"toggle","default":true,"description":"Tag non-speech sounds like laughter, applause, or music."},{"key":"keyterms","label":"Key Terms","type":"text","description":"Comma-separated words or phrases to bias transcription towards (max 1000 terms, 50 chars / 5 words each)."}]}}