Features
3-second voice cloning from audio sample
Multi-language support: English, Chinese, Japanese, Korean
Real-time audio generation output
Hyper-realistic tone and pitch capture
Voice design tool for creating synthetic voices
Secure handling of audio data
User-friendly interface, no technical expertise needed
Character limit on free tier (120 chars per generation)
Commercial use on Pro plan
Priority generation speed for paid users
Download in MP3 or WAV format
Voice model library (community models)
No voice style customization currently
Text-to-speech with emotion tags (angry, sad, excited, etc.)
Voice cloning from 10–15 seconds of audio
2,000,000+ community voice library
Ultra-low latency TTS API
Real-time streaming voice generation
Speech-to-text with multi-speaker and emotion tags
Fish Audio S2.1 Pro: word-level voice control
AI Voice Design: create a custom voice from text prompt
Professional voice cloning (studio-quality verified clones)
Multilingual voice cloning (any voice in multiple languages)
Voice agent end-to-end solution
Podcast transcription tool
Team Plan with collaboration features
Open-source S2 model on GitHub
