{"version":"1","model":{"id":"elevenlabs/text-to-dialogue/eleven-v4","name":"ElevenLabs v4 Dialogue","kind":"audio","availability":"available","available":true,"restricted":false,"api_key_only":false,"description":"Multi-speaker dialogue with Eleven v4: up to ten premade voices, expressive audio tags and natural turn-taking. ArtEmotion limits each dialogue job to 2,000 total characters for reliable HTTP generation.","pricing_note":"Standard provider rate $0.08 per 1,000 spoken characters, summed across all dialogue turns.","categories":["dialog"],"prompt_required":false,"prompt_supported":false,"supports":{},"aspect_ratios":[],"resolutions":[],"durations":[],"base_credits":1,"api_gross_margin_percent":20,"added_at":"2026-10-01","popularity_rank":41,"preview":{"image":"/images/model-previews/generated/elevenlabs-eleven-v4-dialogue-v1.webp"},"schema_url":"/api/v1/models?id=elevenlabs%2Ftext-to-dialogue%2Feleven-v4","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","$id":"https://www.artemotion.ai/api/v1/models?id=elevenlabs%2Ftext-to-dialogue%2Feleven-v4","title":"ElevenLabs v4 Dialogue generation request","description":"Request body accepted by POST /api/v1/generate for elevenlabs/text-to-dialogue/eleven-v4.","type":"object","properties":{"model_id":{"type":"string","const":"elevenlabs/text-to-dialogue/eleven-v4","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","default":0.5,"type":"number","minimum":0,"maximum":1,"multipleOf":0.05},"similarity":{"title":"Voice similarity","default":0.75,"type":"number","minimum":0,"maximum":1,"multipleOf":0.05},"language_code":{"title":"Language code","description":"Optional two-letter ISO code (en, es, fr…). Leave empty for automatic detection; over 90 languages supported.","type":"string","maxLength":2},"apply_text_normalization":{"title":"Text normalization","default":"auto","type":"string","enum":["auto","on","off"]},"seed":{"title":"Seed","description":"-1 for random; reproducibility is best effort.","type":"integer","minimum":-1,"maximum":4294967295},"output_format":{"title":"Output format","default":"mp3_44100_128","type":"string","enum":["mp3_44100_128"]},"previous_text":{"title":"Previous context","description":"Optional preceding text for delivery continuity, not spoken. Up to 100 characters; support depends on the model.","type":"string","maxLength":100},"future_text":{"title":"Following context","description":"Optional following text for delivery continuity, not spoken. Up to 100 characters; 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":"JSON turns, e.g. [{\"voice\":\"Sarah\",\"text\":\"Hello!\"},{\"voice\":\"George\",\"text\":\"Welcome!\"}]. Up to 10 voices and 2,000 total characters."},{"key":"stability","label":"Stability","type":"number","default":0.5,"min":0,"max":1,"step":0.05},{"key":"similarity","label":"Voice similarity","type":"number","default":0.75,"min":0,"max":1,"step":0.05},{"key":"language_code","label":"Language code","type":"text","description":"Optional two-letter ISO code (en, es, fr…). Leave empty for automatic detection; over 90 languages supported."},{"key":"apply_text_normalization","label":"Text normalization","type":"select","default":"auto","options":["auto","on","off"]},{"key":"seed","label":"Seed","type":"integer","min":-1,"max":4294967295,"description":"-1 for random; reproducibility is best effort."},{"key":"output_format","label":"Output format","type":"select","default":"mp3_44100_128","options":["mp3_44100_128"]},{"key":"previous_text","label":"Previous context","type":"text","description":"Optional preceding text for delivery continuity, not spoken. Up to 100 characters; support depends on the model."},{"key":"future_text","label":"Following context","type":"text","description":"Optional following text for delivery continuity, not spoken. Up to 100 characters; support depends on the model."},{"key":"pronunciation_dictionary_locators","label":"Pronunciation dictionaries","type":"array","max_items":3,"description":"Array with pronunciation_dictionary_id and optional version_id; maximum three."}]}}