Features
Real-time voice dictation that polishes speech
Removes filler words (um, uh, you know)
Detects and removes repeated words
Auto-edits when you change your mind mid-sentence
Auto-formats spoken lists and steps
Personalized style and tone adaptation
Personal dictionary for names and terms
Supports 100+ languages with auto-detection
Real-time translation as you speak
Voice edit selected text (shorter, longer, change tone)
Ask questions about selected text (summarize, explain, translate)
Quick answers and actions (search, brainstorm, open pages)
Whisper mode for quiet environments
On-device history storage
Zero cloud data retention
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
