Features
Multilingual text-to-speech in 30 languages
Voice cloning with controllable similarity
Voice design from scratch using text prompts
48kHz high-quality audio output
LoRA training for custom voice adaptation
Diffusion-based speech generation
Emotion and prosody control
Node-based workflow in ComfyUI
Supports multiple speaker references
Tokenizer-free architecture
Model weights in safetensors format
Compatible with ComfyUI visual node editing
Open-source and self-hosted
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
