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
400+ natural voices in 80+ languages
AI talking photo with lip-sync
AI voice cloning and customization
AI video translation with lip-sync
AI montage maker from long videos
AI clip generator for viral shorts
AI photo generator from text prompts
Text to speech with emotional tones
