Main features: AI voice cloning, supporting audio sample upload (MP3, WAV, M4A formats, 5-30 seconds, <4.5MB) or direct recording, text input to generate cloned voice. Cross-language synthesis (English, Chinese, Japanese, Korean), with selected AI voice models like Donald Trump, Alex, Sophia, Zhuge Liang, Jay Chou available. Key features: Free to use, no subscription; fast cloning (10-30 seconds); preview and download; free version 70.5% similarity, speed and pitch adjustment; professional version offers 99.5% similarity, emotion control, accent marking, whisper mode. Target users: Personal project users, content creators; professional version for commercial users. Core advantages: 100% free; high similarity; multilingual support; data security (audio data not shared); mobile compatibility. Typical use cases: Content creation like videos, podcasts, audiobooks. Pricing: Free version with limits (max 20 characters per use, ~1200 seconds per month); professional version ￥69.89/month (annual ￥839), offering instant processing, longer text (1000+ characters), more realistic results, unlimited voice cloning.
