Features
10+ ASR engines: Volcengine, OpenAI, Gemini, DashScope, ElevenLabs, SiliconFlow, Soniox
Offline ASR: SenseVoice, Paraformer, Funasr Nano
LLM text post-processing: punctuation, formatting, translation
Cross-keyboard floating ball for voice input on any keyboard
Fcitx integration via AIDL for long-press voice input
SiliconFlow partnership: pre-configured ASR & LLM models out-of-box
Privacy-first: zero data collection, local storage only
Material3 design with dynamic color (Monet) and dark/light mode
Compact keyboard layout with three adjustable heights
Global undo for post-processing
Custom preset prompts for LLM
Pro only: traditional Chinese conversion, regex post-processing, hotword management
Pro only: WebDAV backup, glowing cursor swipe, custom UI color
Android 10+ with target Android 15
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
