Features
Voice cloning from 3 seconds of audio
Seven TTS engines (e.g., Qwen, Chatterbox)
Timeline-based Stories Editor for multi-voice narratives
Audio effects pipeline: pitch shift, reverb, delay, compression, presets
Whisper-based transcription (Base, Small, Medium, Large, Turbo)
Refined transcripts using local LLM to remove disfluencies
Dictation mode: capture audio alongside transcripts, paste anywhere
Unlimited generation length up to 50,000 characters
MCP (Model Context Protocol) integration for agent speech
Personalities system: rewrite or compose in character
Local GPU inference: Metal, CUDA, ROCm, Intel Arc, DirectML
One-click remote server setup with automatic discovery
Cross-platform: macOS, Windows, Linux
Open source under MIT license
Optional $VOICEBOX token for community support
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
