VoxShift
VoxShift is a free desktop app that transforms microphone audio in real time using Retrieval-based Voice Conversion (RVC).
What VoxShift is
VoxShift is a free desktop app that transforms microphone audio in real time using Retrieval-based Voice Conversion (RVC). It runs on Windows, macOS, and Linux and is intended for people who want voice conversion in voice chat, games, or video calls without writing code. Its listed controls include pitch and formant shift, index ratio, input and output gain, monitor mode, and noise gate or suppression. The README describes a marketplace for downloading community voice models in categories such as anime, masculine, feminine, character, and robotic. It also describes training a voice using WAV, MP3, FLAC, or OGG files, with users choosing training epochs and a pitch extraction algorithm. Audio processing happens on the user's machine, and the project says it has no telemetry, analytics, crash reporting, or user accounts. Network calls are limited to marketplace metadata and optional GitHub updates. The README lists under 200 ms end-to-end latency on a modern GPU, but real-time inference requires PyTorch with CUDA, ROCm, or Metal support for GPU acceleration. The repository is MIT licensed, and its Releases page has no available releases.
Good
- Processes audio on the user's machine.
- Lists voice controls and voice training.
- No telemetry, analytics, crash reporting, or user accounts.
- Free and open source under an MIT license.
Watch out
- Real-time inference requires supported GPU acceleration.
- The Releases page has no available releases.
- A virtual audio driver is listed for each platform.
Who it suits
VoxShift is aimed at people who want to change their microphone voice for chats, games, or video calls without coding. It suits users whose computer can meet the stated GPU acceleration requirement.
Verdict
VoxShift offers local, real-time voice conversion with controls, community models, and voice training. Check the GPU requirement and release availability before relying on it for a setup.
Plans and prices
From VoxShift's own pricing page, checked 7 Oct 2026.
| Plan | Price | What it gives you |
|---|---|---|
| Free | Free | Free and open source · local use |
The facts
Each one read from VoxShift's own pages, with the date it was checked.
What it does
- Audio controls
- Listed controls include pitch shift, formant shift, index ratio, input and output gain, monitor mode, and noise gate or suppression.checked 7 Oct 2026
- Download availability
- The repository's Releases page states that there are no releases available.checked 7 Oct 2026
- Hardware requirement
- The README says real-time inference requires PyTorch with CUDA, ROCm, or Metal support for GPU acceleration.checked 7 Oct 2026
- Integrations
- The README describes routing processed audio through a virtual cable for use as a microphone in Discord, OBS, and Zoom.checked 7 Oct 2026
- Intended audience
- The README presents VoxShift for people who want to use AI voice conversion in voice chat, games, or video calls without writing code.checked 7 Oct 2026
- Latency
- The README lists under 200 ms end-to-end latency on a modern GPU.checked 7 Oct 2026
- License
- The repository identifies the project as MIT licensed.checked 7 Oct 2026
- Local processing
- The project says audio processing happens on the user's machine and audio never leaves the computer.checked 7 Oct 2026
- Network calls
- The README says network calls are limited to the marketplace API for metadata and opt-in GitHub auto-updates.checked 7 Oct 2026
- Privacy
- The README says VoxShift has zero telemetry, no analytics or crash reporting, and no user accounts.checked 7 Oct 2026
- Purpose
- VoxShift is a desktop app that transforms microphone audio in real time using Retrieval-based Voice Conversion (RVC).checked 7 Oct 2026
- Virtual audio drivers
- The README lists VB-Audio VB-Cable for Windows, BlackHole 2ch for macOS, and a PipeWire virtual sink for Linux.checked 7 Oct 2026
- Voice marketplace
- The README describes browsing and one-click downloading community voice models from voice-models.com, with categories including anime, masculine, feminine, character, and robotic.checked 7 Oct 2026
- Voice training
- The README says users can train a voice by dropping WAV, MP3, FLAC, or OGG files and choosing training epochs and a pitch extraction algorithm.checked 7 Oct 2026
Alternatives to VoxShift
- 1
Voice.ai
Free planAndroidiOSWebAPI8.3From $5 a month - 2
BadloVoice
Free planOpen sourceAndroidiOSWebAPI7.9Free plan - 3
FineVoice AI Voice Changer
Free planWebAPImacOSWindows7.8Free plan - 4
EaseUS VoiceWave
Free planAndroidiOSWebWindows7.6From $24.97 a year - 5
iMyFone MagicMic
Free planAndroidiOSmacOSWindows7.5From $45.99 a year - 6
FineShare VoiceTrans
Free planiOSWebmacOSWindows7.4$5.99 one-time