{"version":"1","model":{"id":"elevenlabs/text-to-dialogue/eleven-v3","name":"ElevenLabs Text to Dialogue","kind":"audio","availability":"available","available":true,"restricted":false,"api_key_only":false,"description":"Generate multi-speaker dialogue audio by assigning each line of dialogue to an ElevenLabs voice. Powered by Eleven v3.","pricing_note":"~$0.10 / 1k chars of dialogue text","categories":["dialog"],"prompt_required":false,"prompt_supported":false,"supports":{},"aspect_ratios":[],"resolutions":[],"durations":[],"base_credits":7,"api_gross_margin_percent":20,"added_at":"2026-05-24","popularity_rank":29,"preview":{"image":"/images/model-previews/generated/elevenlabs-dialogue-eleven-v3-v1.webp"},"schema_url":"/api/v1/models?id=elevenlabs%2Ftext-to-dialogue%2Feleven-v3","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","$id":"https://www.artemotion.ai/api/v1/models?id=elevenlabs%2Ftext-to-dialogue%2Feleven-v3","title":"ElevenLabs Text to Dialogue generation request","description":"Request body accepted by POST /api/v1/generate for elevenlabs/text-to-dialogue/eleven-v3.","type":"object","properties":{"model_id":{"type":"string","const":"elevenlabs/text-to-dialogue/eleven-v3","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"},"inputs":{"type":"array","minItems":1,"maxItems":100,"description":"Dialogue turns using premade voice names. Maximum 10 different voices and 2,000 total text characters per job.","items":{"type":"object","additionalProperties":false,"required":["voice","text"],"properties":{"voice":{"type":"string","description":"Premade voice name, for example Rachel or Sarah. Raw provider IDs and cloned voices are not supported in dialogue."},"text":{"type":"string","minLength":1,"maxLength":2000}}}},"stability":{"title":"Stability","description":"Voice stability (0–1). Higher = more consistent, lower = more expressive.","default":0.5,"type":"number","minimum":0,"maximum":1,"multipleOf":0.05},"language_code":{"title":"Language","description":"Language of the input text. Auto-detected if not set.","default":"","type":"string","enum":["","en","zh","es","hi","pt","fr","de","ja","ar","ko","id","it","nl","tr","pl","sv","fil","ms","ro","uk","el","cs","da","fi","bg","hr","sk","ta","ru"]},"apply_text_normalization":{"title":"Text Normalization","description":"Whether to convert numbers, URLs, and symbols to spoken words. 'Auto' applies it selectively.","default":"auto","type":"string","enum":["auto","on","off"]},"seed":{"title":"Seed","description":"Seed for reproducibility. -1 for random.","type":"integer","minimum":-1,"maximum":4294967295},"previous_text":{"title":"Previous context","description":"Optional preceding text for continuity; not spoken. Support depends on the model.","type":"string","maxLength":100},"future_text":{"title":"Following context","description":"Optional following text for continuity; not spoken. Support depends on the model.","type":"string","maxLength":100},"pronunciation_dictionary_locators":{"type":"array","maxItems":3,"items":{"type":"object","additionalProperties":false,"required":["pronunciation_dictionary_id"],"properties":{"pronunciation_dictionary_id":{"type":"string","minLength":1},"version_id":{"type":"string","minLength":1}}}}},"required":["model_id","inputs"],"additionalProperties":false},"parameters":[{"key":"inputs","label":"Dialogue Inputs","type":"array","min_items":1,"max_items":100,"required":true,"description":"Array of dialogue turns, each with a voice and a line of text. At least one turn is required."},{"key":"stability","label":"Stability","type":"number","default":0.5,"min":0,"max":1,"step":0.05,"description":"Voice stability (0–1). Higher = more consistent, lower = more expressive."},{"key":"language_code","label":"Language","type":"select","default":"","options":["","en","zh","es","hi","pt","fr","de","ja","ar","ko","id","it","nl","tr","pl","sv","fil","ms","ro","uk","el","cs","da","fi","bg","hr","sk","ta","ru"],"description":"Language of the input text. Auto-detected if not set."},{"key":"apply_text_normalization","label":"Text Normalization","type":"select","default":"auto","options":["auto","on","off"],"description":"Whether to convert numbers, URLs, and symbols to spoken words. 'Auto' applies it selectively."},{"key":"seed","label":"Seed","type":"integer","min":-1,"max":4294967295,"description":"Seed for reproducibility. -1 for random."},{"key":"previous_text","label":"Previous context","type":"text","description":"Optional preceding text for continuity; not spoken. Support depends on the model."},{"key":"future_text","label":"Following context","type":"text","description":"Optional following text for continuity; not spoken. Support depends on the model."},{"key":"pronunciation_dictionary_locators","label":"Pronunciation Dictionaries","type":"array","max_items":3,"description":"Array of pronunciation dictionary locators, each with pronunciation_dictionary_id and version_id. Up to 3 supported. Advanced use only."}]}}