Reference Voice Translation
Outputs translated speech in a voice close to your reference voice.
VoxShift transcribes and translates your microphone input, then outputs translated speech with reference-voice synthesis for Discord, game voice chat, OBS, and meeting apps.
Opponent audio is translated as subtitles, so conversations with friends, viewers, and teammates are supported by both voice and captions.
Supported Languages
Outputs translated speech in a voice close to your reference voice.
Helps route translated audio to voice chat apps through virtual audio.
Your speech is output as voice while opponent audio is translated as subtitles.
Walks through microphone, output, language, and reference-voice setup.
Sends original and translated captions to OBS for streams.
Checks GPU, VRAM, model status, and audio devices before live use.
The bidirectional mode is asymmetric to reduce GPU load and latency. Your speech is voiced, while opponent speech is translated into subtitles.
Voice output
Subtitle translation
Talk with overseas friends in a foreign language using your own voice.
Send callouts, tactics, and reactions as translated speech.
Add translated voice and captions for international viewers.
Usable in meetings, though the main focus is VC, streaming, and games.
Free
Coming SoonMicrosoft Store
Store準備中Sales are moving to Microsoft Store. Once published, VoxShift will be available there.
VoxShift depends on GPU performance. Please test with Free Edition before purchasing.
No. VoxShift is semi-real-time voice translation, and latency varies by environment.
Yes. In the first version, opponent audio is translated as subtitles.
Not in the first version. Overlapping speech may reduce accuracy.
No. It aims for speech close to your reference voice, not perfect reproduction.
No. Voices without consent are prohibited.
VoxShift depends on GPU performance. Please test with Free Edition before purchasing.