EchoVeil

About

EchoVeil transforms your voice in real-time on any browser tab. Whether you're on a voice call, watching a stream, or reading aloud — EchoVeil converts the audio through an AI voice of your choice, live.

HOW IT WORKS
1. Upload a short voice clip (~15 seconds) to create a persona
2. Optionally add a face photo for lip-synced avatar animation
3. Open any tab with audio and click Start
4. Your audio is converted in real-time through AI voice conversion

KEY FEATURES
- Real-time voice conversion powered by Seed-VC
- Audio-driven face animation with lip-sync (MuseTalk)
- Multiple personas — switch voices instantly
- Works on any browser tab (YouTube, calls, streams)
- Runs entirely on YOUR machine — nothing leaves your computer
- Open-source server (GPL-3.0)

REQUIREMENTS
- Windows 10/11 with NVIDIA GPU (RTX 3060 or better recommended)
- EchoVeil Server (free, open-source) — download at https://github.com/mexican75/echoveil-server
- 8GB+ VRAM recommended for voice + face animation

PRIVACY
All AI processing runs locally on your machine. No audio is sent to any cloud service. The only network communication is account authentication with our servers. See our privacy policy at https://echoveil.app/privacy.html

30-minute free trial included. One-time purchase for full access.