Main Features
- Voice Cloning: Upload 5-30 second audio samples or record directly to generate AI voice similar to original
- Text-to-Speech: Input text for cloned voice to read
- Cross-language Synthesis: Supports English, Chinese, Japanese, Korean and more
- Preset Voice Models: Provides celebrity voice models like Trump, Jay Chou, Zhuge Liang
Usage Process
- Provide Voice Sample: Upload audio file (MP3, WAV, M4A, 5-30s, <4.5MB) or record directly
- Enter Synthesis Text: Input content to be read in text box
- Start Cloning: Click 'Clone Voice' button to process
- Preview & Download: Preview generated effect and download audio file
Pricing Plans
- Free: 500 characters TTS quota, 20 characters per input, 70.5% similarity
- Pro ($4.59/month): Unlimited voice cloning, 200k characters TTS, 1000 characters per input, 99.5% similarity, commercial rights
- Unlimited ($10.90/month): Unlimited voice cloning and TTS characters, 5000 characters per input
Technical Features
- Fast processing: Complete cloning in 10-30 seconds
- High similarity: Up to 99.5% for paid versions
- Supports emotion preservation and accent maintenance
- Mobile compatible
Usage Restrictions
- Free version limited to ~1200 seconds audio monthly
- Prohibited for fraud, hate speech, adult content
- Commercial use requires paid version
Target Users
- Content creators
- Video producers
- Podcast hosts
- Personal project developers
- Collection Time：2025-09-16
-
Pricing Mode：
Freemium
Paid
#Text to speech
#Voice Modulation
Freemium
Paid
Website
