OpenVoiceChanger

Free plan APILinuxSelf-hostedWebWindows

What OpenVoiceChanger is

OpenVoiceChanger is a free, open-source, self-hosted web application for real-time AI voice conversion with ONNX or RVC models. It streams microphone audio over WebSockets and can also apply DSP voice effects without a conversion model. The studio offers pitch and formant shifting, 16 F0 methods, 12 DSP effects and 16 built-in voice presets; users can save custom presets with all Voice Lab settings. For offline conversion, it accepts WAV, MP3, FLAC, OGG and M4A files and renders WAV output, with a configured maximum of 600 seconds. It supports ONNX and RVC PyTorch .pth or .pt models; RVC requires a HuBERT content encoder. The backend provides HTTP endpoints for health, models, presets and conversion, plus a WebSocket endpoint for live audio. The app supports Linux and Windows and lists Python 3.10 or later, Node.js 20.19 or later, and npm as requirements. Recorded takes are stored in browser IndexedDB on the same origin and may be cleared or evicted by the browser.

Who it suits

OpenVoiceChanger suits people seeking a self-hosted browser tool for live or file-based voice conversion. Users working with RVC models need a HuBERT content encoder, and the listed software requirements include Python, Node.js and npm.

What it does well

Free and open source under the MIT license
Offers 16 built-in voice presets
Supports five input audio formats
Provides HTTP and WebSocket endpoints

What to know first

Offline conversion is limited to 600 seconds
RVC requires a HuBERT content encoder
Browser-stored takes may be cleared or evicted
No third-party conferencing integrations are listed

Limits

Offline conversion has a configured maximum duration of 600 seconds. RVC model use requires a HuBERT content encoder.

Getting started

Visit the OpenVoiceChanger GitHub repository.
Prepare Python 3.10 or later, Node.js 20.19 or later, and npm.
Install and launch the application using its managed launcher.
Open the application in a browser.
Use an ONNX model or an RVC PyTorch .pth or .pt model; RVC also requires a HuBERT content encoder.

Verdict

OpenVoiceChanger combines live conversion, DSP effects and offline file processing in a self-hosted browser app. Check the model requirements and duration limit, and note that saved takes rely on browser storage.

Questions

Is OpenVoiceChanger free?

Yes. It is listed as free and open source.

What license does it use?

The repository identifies the license as MIT.

Which platforms does it support?

It supports browser use and lists Linux, Windows, API, and self-hosted platforms.

Can it convert recorded audio?

Yes. It accepts WAV, MP3, FLAC, OGG, and M4A files and renders WAV output, up to a configured maximum of 600 seconds.

Which model formats does it support?

It supports ONNX models and RVC PyTorch .pth or .pt models. RVC requires a HuBERT content encoder.

Does it integrate with conferencing apps?

The README documents ONNX Runtime, PyTorch, RVC, and GitHub Releases for updates; it does not list third-party conferencing integrations.

Facts from OpenVoiceChanger's own pages

API: The backend exposes HTTP endpoints for health, models, presets, conversion, and updates, plus a WebSocket endpoint for real-time audio. · github.com, 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, 9 Oct 2026
Custom presets: Users can save custom presets containing the complete Voice Lab settings. · github.com, 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, 9 Oct 2026
Effects: Its server-side DSP rack includes 12 effects, including noise gate, distortion, chorus, echo, reverb, EQ, and compression. · github.com, 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, 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, 4 Oct 2026
License: The repository is distributed under the MIT License. · github.com, 9 Oct 2026
Live conversion: It streams microphone audio over WebSockets and also supports model-free DSP voice effects. · github.com, 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, 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, 4 Oct 2026
Models: It accepts ONNX and RVC .pth or .pt models, and RVC models require a HuBERT content encoder file. · github.com, 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, 9 Oct 2026
Platforms: The README documents Windows setup and says other platforms use manual setup; its Makefile supports POSIX shells or WSL. · github.com, 9 Oct 2026
Product: OpenVoiceChanger is a self-hosted web application for real-time AI voice conversion using ONNX or RVC models. · github.com, 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, 9 Oct 2026
Realtime conversion: It streams audio over WebSockets and supports ONNX, RVC, and model-free DSP modes. · github.com, 9 Oct 2026
Requirements: The documented requirements include Python 3.10 or later, Node.js 20.19 or later, and npm. · github.com, 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, 4 Oct 2026
Updates: The app checks public GitHub releases but installs an update only after a user action through the managed launcher. · github.com, 9 Oct 2026
Voice controls: The studio offers live pitch and formant shifting, 16 F0 methods, RVC controls, and 16 built-in voice presets. · github.com, 9 Oct 2026