{"version":"1","model":{"id":"fal-ai/ai-avatar/multi-text","name":"AI Avatar Multi (Text)","kind":"video","availability":"available","available":true,"restricted":false,"api_key_only":false,"description":"AI Avatar Multi Text generates a two-person talking video from a portrait photo and typed dialogue — each speaker gets a separate voice.","categories":["lipsync"],"prompt_required":false,"prompt_supported":true,"supports":{"startImage":true},"requires":{"startImage":true},"aspect_ratios":[],"resolutions":["480p","720p"],"durations":[],"base_credits":83,"api_gross_margin_percent":20,"added_at":"2026-05-22","popularity_rank":390,"example_prompt":"Upload a portrait photo, type what each speaker says, pick voices — AI Avatar Multi generates a two-person talking video with lip-sync","preview":{"video":"https://cdn.artemotion.ai/file/artemotion-ai-bckt/model-previews/ai-avatar-multi-text-fal-v1-sm.mp4"},"schema_url":"/api/v1/models?id=fal-ai%2Fai-avatar%2Fmulti-text","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","$id":"https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fai-avatar%2Fmulti-text","title":"AI Avatar Multi (Text) generation request","description":"Request body accepted by POST /api/v1/generate for fal-ai/ai-avatar/multi-text.","type":"object","properties":{"model_id":{"type":"string","const":"fal-ai/ai-avatar/multi-text","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"},"acceleration":{"title":"Acceleration","description":"The acceleration level to use for generation.","default":"regular","type":"string","enum":["none","regular","high"]},"voice2":{"title":"Voice2","description":"The second person's voice to use for speech generation","default":"Roger","type":"string","enum":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"]},"second_text_input":{"title":"Second Text Input","description":"The text input to guide video generation.","type":"string"},"seed":{"title":"Seed","description":"Random seed for reproducibility. If None, a random seed is chosen.","default":81,"type":"integer","minimum":0,"maximum":4294967295},"voice1":{"title":"Voice1","description":"The first person's voice to use for speech generation","default":"Sarah","type":"string","enum":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"]},"num_frames":{"title":"Num Frames","description":"Number of frames to generate (41–241). Frames above 81 are billed at 1.25×.","default":191,"type":"number","minimum":41,"maximum":241,"multipleOf":1},"first_text_input":{"title":"First Text Input","description":"The text input to guide video generation.","type":"string"},"resolution":{"type":"string","enum":["480p","720p"]},"image_url":{"type":"string","format":"uri"}},"required":["model_id","second_text_input","first_text_input","image_url"],"additionalProperties":false},"parameters":[{"key":"acceleration","label":"Acceleration","type":"select","default":"regular","options":["none","regular","high"],"description":"The acceleration level to use for generation."},{"key":"voice2","label":"Voice2","type":"select","default":"Roger","options":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"],"description":"The second person's voice to use for speech generation"},{"key":"second_text_input","label":"Second Text Input","type":"text","required":true,"description":"The text input to guide video generation."},{"key":"seed","label":"Seed","type":"seed","default":81,"min":0,"max":4294967295,"description":"Random seed for reproducibility. If None, a random seed is chosen."},{"key":"voice1","label":"Voice1","type":"select","default":"Sarah","options":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"],"description":"The first person's voice to use for speech generation"},{"key":"num_frames","label":"Num Frames","type":"number","default":191,"min":41,"max":241,"step":1,"description":"Number of frames to generate (41–241). Frames above 81 are billed at 1.25×."},{"key":"first_text_input","label":"First Text Input","type":"text","required":true,"description":"The text input to guide video generation."}]}}