{"version":"1","model":{"id":"fal-ai/minimax/voice-clone","name":"MiniMax Voice Clone","kind":"audio","availability":"available","available":true,"restricted":false,"api_key_only":false,"description":"Clone any voice from a 10+ second audio sample using MiniMax's voice cloning model.","pricing_note":"$1.50 per voice clone + $0.30/1k chars of preview text","categories":["clone"],"prompt_required":false,"prompt_supported":true,"supports":{"referenceAudio":true},"requires":{"referenceAudio":true},"aspect_ratios":[],"resolutions":[],"durations":[],"reference_audio_duration":{"min_seconds":10},"base_credits":188,"api_gross_margin_percent":20,"added_at":"2026-05-22","popularity_rank":41,"example_prompt":"Upload a 10+ second audio sample — MiniMax clones the voice and generates a preview of the cloned voice speaking.","preview":{"image":"/images/model-previews/generated/minimax-voice-clone-v1.webp"},"schema_url":"/api/v1/models?id=fal-ai%2Fminimax%2Fvoice-clone","input_schema":{"$schema":"https://json-schema.org/draft/2020-12/schema","$id":"https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fminimax%2Fvoice-clone","title":"MiniMax Voice Clone generation request","description":"Request body accepted by POST /api/v1/generate for fal-ai/minimax/voice-clone.","type":"object","properties":{"model_id":{"type":"string","const":"fal-ai/minimax/voice-clone","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"},"noise_reduction":{"title":"Noise Reduction","description":"Apply noise reduction to the input audio before cloning.","default":false,"type":"boolean"},"need_volume_normalization":{"title":"Volume Normalization","description":"Normalize the volume of the input audio before cloning.","default":false,"type":"boolean"},"model":{"title":"Preview Model","description":"TTS model used to generate the preview sample with the cloned voice.","default":"speech-02-hd","type":"string","enum":["speech-02-hd","speech-02-turbo","speech-01-hd","speech-01-turbo"]},"accuracy":{"title":"Accuracy","description":"Text validation accuracy threshold (0–1). Lower values are more permissive.","default":0.5,"type":"number","minimum":0,"maximum":1,"multipleOf":0.01},"audio_url":{"type":"string","format":"uri"}},"required":["model_id","audio_url"],"additionalProperties":false},"parameters":[{"key":"noise_reduction","label":"Noise Reduction","type":"toggle","default":false,"description":"Apply noise reduction to the input audio before cloning."},{"key":"need_volume_normalization","label":"Volume Normalization","type":"toggle","default":false,"description":"Normalize the volume of the input audio before cloning."},{"key":"model","label":"Preview Model","type":"select","default":"speech-02-hd","options":["speech-02-hd","speech-02-turbo","speech-01-hd","speech-01-turbo"],"description":"TTS model used to generate the preview sample with the cloned voice."},{"key":"accuracy","label":"Accuracy","type":"number","default":0.5,"min":0,"max":1,"step":0.01,"description":"Text validation accuracy threshold (0–1). Lower values are more permissive."}]}}