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
Real-time noise cancellation with system-level audio processing
AI Meeting Copilot with GPT-4 summaries and action items
Meeting transcription with speaker identification
Accent conversion for both speaker and listener sides
On-device processing for low latency and privacy
Voice translation in 80+ languages
Call Center AI with voice isolation and after-call summaries
VIVA 2.0 platform for building voice AI agents
Webhook and MCP integration support
Desktop apps for Windows and Mac
Mobile apps for iOS and Android
SOC 2 Type II and GDPR compliance
Voice Security and Speech Analytics (new in 2026)
Compatibility with 800+ communication apps
