- Home
- AI Voice Changer Software
- OpenVoiceChanger
OpenVoiceChanger
What it is
OpenVoiceChanger is a free, MIT-licensed, self-hosted web application for real-time AI voice conversion. It streams microphone audio over WebSockets and can also apply model-free DSP effects. The studio provides pitch and formant shifting, 16 F0 methods, 12 DSP effects, and 16 built-in voice presets, while custom presets can save complete Voice Lab settings. An offline converter accepts WAV, MP3, FLAC, OGG, and M4A files and renders WAV output up to a configured 600-second maximum. Models may use ONNX or RVC PyTorch .pth or .pt formats; RVC requires a HuBERT content encoder. The backend exposes HTTP endpoints for health, models, presets, and conversion, plus a WebSocket endpoint for live audio. It runs with a local browser interface on Linux or Windows and requires Python 3.10 or later, Node.js 20.19 or later, and npm. Recorded takes remain in browser IndexedDB and may be cleared by the browser.
For and against
For
- Real-time microphone conversion over WebSockets
- Supports ONNX and RVC models
- Model-free DSP effects available
- Converts several audio file formats
- Custom presets save full settings
Against
- RVC models require a HuBERT encoder
- Recorded browser takes may be evicted
- Installation requires Python, Node.js, and npm
- No third-party conferencing integrations listed
The verdict
OpenVoiceChanger combines live model-based conversion, DSP effects, and offline file rendering in a self-hosted browser setup. Its technical requirements and local-storage behavior matter for deployment planning.
Who it suits
It suits self-hosters, streamers, and audio creators needing live or recorded voice conversion. Users should be comfortable installing the listed Python, Node.js, and npm requirements.
On the record
- API
- The backend exposes HTTP endpoints for health, models, presets, conversion, and updates, plus a WebSocket endpoint for real-time audio.github.com · read 9 Oct 2026
- Checkpoint security
- Uploaded RVC checkpoints use PyTorch safe weights-only loading by default; unsafe loading requires an explicit deployment setting.github.com · read 9 Oct 2026
- Custom presets
- Users can save custom presets containing the complete Voice Lab settings.github.com · read 4 Oct 2026
- Deployment
- The app runs a local backend and browser UI, with the backend bound to 127.0.0.1 by default.github.com · read 9 Oct 2026
- Effects
- Its server-side DSP rack includes 12 effects, including noise gate, distortion, chorus, echo, reverb, EQ, and compression.github.com · read 9 Oct 2026
- File conversion
- Users can upload WAV, MP3, FLAC, OGG, or M4A files for conversion to downloadable WAV, with a configurable maximum length of 600 seconds.github.com · read 9 Oct 2026
- Integrations
- The README documents ONNX Runtime, PyTorch, RVC, and GitHub Releases for updates; it does not list third-party conferencing integrations.github.com · read 4 Oct 2026
- License
- The repository is distributed under the MIT License.github.com · read 9 Oct 2026
- Live conversion
- It streams microphone audio over WebSockets and also supports model-free DSP voice effects.github.com · read 4 Oct 2026
- Local storage
- Recorded takes are stored in browser IndexedDB on the same origin and may be cleared or evicted by the browser.github.com · read 4 Oct 2026
- Model formats
- The app supports ONNX models and RVC PyTorch .pth or .pt models, with RVC requiring a HuBERT content encoder.github.com · read 4 Oct 2026
- Models
- It accepts ONNX and RVC .pth or .pt models, and RVC models require a HuBERT content encoder file.github.com · read 9 Oct 2026
- Network security
- Cross-origin HTTP and WebSocket requests are checked against an origin allowlist, and the README recommends HTTPS for LAN microphone access.github.com · read 9 Oct 2026
- Product
- OpenVoiceChanger is a self-hosted web application for real-time AI voice conversion using ONNX or RVC models.github.com · read 4 Oct 2026
- Purpose
- OpenVoiceChanger is a real-time AI voice changer web application that routes a microphone through ONNX or RVC models.github.com · read 9 Oct 2026
- Realtime conversion
- It streams audio over WebSockets and supports ONNX, RVC, and model-free DSP modes.github.com · read 9 Oct 2026
- Requirements
- The documented requirements include Python 3.10 or later, Node.js 20.19 or later, and npm.github.com · read 9 Oct 2026
- Security
- The backend binds to localhost by default, checks browser origins for HTTP and WebSocket requests, and loads RVC checkpoints in safe weights-only mode by default.github.com · read 4 Oct 2026
