Features
Zero-shot voice cloning from 3-second clip
Voice design: gender, age, accent, pitch, style, dialect
Video dubbing: transcribe, translate, re-voice, export MP4
Vocal isolation (Demucs-based speech/music separation)
Multi-speaker diarization (Pyannote + WhisperX)
Real-time TTS preview via floating widget
Batch queue for drag-and-drop bulk video processing
Voice library with browsing, favoriting, tagging, profile conversion
A/B voice comparison for casting decisions
Selective track export, SRT/VTT subtitle export, stem export
Per-segment gain control (0–200%)
Invisible watermarking (AudioSeal) with detection API
Keyboard shortcuts: ⌘+Enter generate, ⌘+S save, undo/redo
Live telemetry: CPU/RAM/VRAM stats with model warm-up indicator
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
