VoxShift
Windows voice translation software

Speak foreign-language VC in your own 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.

Partner subtitles translate the other person's speech into text, so conversations with friends, viewers, and teammates are supported by both voice and captions.

VoxShift Live tab in English showing the language pair, translation mode, the Now and History panels, and the input level.
Windows 10/11Discord / Game VC / OBS10 LanguagesReference VoiceBidirectional SubtitlesSteam / Microsoft Store

Supported Languages

日本語English中文한국어DeutschFrançaisРусскийPortuguêsEspañolItaliano日本語English中文한국어DeutschFrançaisРусскийPortuguêsEspañolItaliano
Problem

In overseas voice chat, are you losing more than words?

Caption translation helps you read, but it does not let others hear you speak. Generic TTS removes your identity, and voice changers do not translate language. VoxShift is built for the gap between translation tools and real voice chat.

Captions alone do not join the conversation

In VC, being able to read is not the same as being able to answer with your voice.

Generic TTS erases your presence

Even when the words are translated, a generic synthetic voice can feel detached from you.

Meeting tools do not fit Discord or games

VoxShift is designed around virtual mic output, monitoring, OBS captions, and game-friendly routing.

Features

Voice translation designed for voice chat.

Reference Voice Translation

Speaks the translation in a voice close to yours, based on a short optional recording or your live voice.

Fast / Quality Modes

Fast starts translating before you finish the sentence; Quality waits for more context. Choose on the Live tab.

Now / History View

The Live tab shows what is being said in Now and finished lines in History, newest first.

Discord / Game VC Ready

Sends translated voice to Discord, games, and OBS through a virtual audio device. Monitor lets you hear it yourself.

Bidirectional Subtitles

Your speech is output as voice, while the other person's speech (call, game, or video audio) is translated as subtitles.

OBS Caption Support

Shows subtitles in the built-in subtitle window or sends original and translated captions to an OBS text source.

Setup Wizard

Walks through display language, quality for your PC, languages, microphone and output, and an optional voice recording.

Low VRAM Modes

Checks your PC's GPU memory and CPU, then picks Standard, Low VRAM, or Ultra-low VRAM. Change it in Performance → Manual settings.

Live Start Check

The Live tab checks whether Live can start with your current settings; the Performance tab shows estimated VRAM.

Bidirectional Mode

You speak with your voice. Others reach you as subtitles.

The bidirectional mode is asymmetric to reduce GPU load and latency. Your speech is voiced, while the other person's speech is translated into subtitles.

You → Others

  1. Speak
  2. Voice Recognition
  3. Translation Engine
  4. Voice Synthesis
  5. Virtual Mic

Voice output

Others → You

  1. Desktop audio capture
  2. Voice recognition
  3. Translation engine
  4. Subtitles
  5. Log saving

Subtitle translation

Demo

Check the actual flow before buying

These screenshots are captured from the current VoxShift app running on a local PC. Instead of a browser demo that hides PC requirements, the free version (Steam Demo / Microsoft Store free trial) lets you check your GPU, audio devices, and whether Live can start on your own PC.

VoxShift Live tab in English showing the language pair, translation mode, the Now and History panels, and the input level.

Live Translation Console

  • Language pair
  • Fast / Quality
  • Now
  • History
  • Input level
VoxShift Audio tab in English showing microphone input, translated voice output, monitor output, and volume settings.

Audio Route for Discord / Games

  • Microphone input
  • Translated voice output
  • Monitor (hear it yourself)
  • Volume
  • Clipping protection
VoxShift Audio tab in English showing OBS subtitle settings: obs-websocket host and port, text source, and subtitle mode.

OBS Caption Integration

  • OBS WebSocket
  • Text source update
  • Translation only
  • Source + translation
VC Toolkit

Turn translation into tools you can use in voice chat.

The core is still reference-voice translation. Around it, Soundboard, voice polish, and routing views make it easier to imagine how VoxShift fits Discord, game VC, and OBS after purchase.

Core

Reference voice translation + subtitles

Support

Soundboard / EQ / Routing

VoxShift Audio tab in English showing output and monitor routing, with a soundboard and voice polish overlay.

Soundboard cues

Ready
On my wayNiceWaitAgain?ThanksReady

Voice polish

NoiseOn
EQ+2 dB
Clipping protectionSafe

One-shot cues

Soundboard

Keep short confirmations and reactions ready, so waiting for a translation does not stop the flow of VC.

  • Short replies
  • Stream reactions
  • Game callouts

Noise / EQ / Clipping protection

Audio Polish

Translated voice is easier to use when cleanup, EQ, and clipping protection are part of the same workflow.

  • Noise suppression
  • EQ adjustment
  • Clipping protection

VC / Monitor / OBS

Routing View

Check virtual mic, monitor output, and OBS captions as one route to reduce setup mistakes.

  • Translated voice output
  • Monitor output
  • OBS captions
Use Cases

Built for more than meeting rooms.

Discord

Talk with overseas friends in a foreign language using your own voice.

Game VC

Send callouts, tactics, and reactions as translated speech.

OBS / Streaming

Add translated voice and captions for international viewers.

Online Meetings

Usable in meetings, though the main focus is VC, streaming, and games.

Guides

Find the VoxShift workflow that matches your search.

These pages break down the main ways people look for voice translation: Discord, game voice chat, OBS captions, reference voice, Windows setup, and local-first processing.

Discord Voice Translator

Translate Discord voice chat with your own voice.

Translate Discord voice chat on Windows with reference-voice speech output, virtual mic routing, partner subtitles, and a free version to test first.

Game Voice Chat Translation

Voice translation for game chat with soundboard cues.

Translate your microphone for game voice chat, Discord calls, OBS streams, and international teams with VoxShift for Windows. Free version on Steam and Microsoft Store.

OBS Translation Captions

Add translated captions and translated voice to OBS.

Add translated captions and reference-voice translated speech to OBS streams with VoxShift for Windows. Supports OBS WebSocket text source updates.

Reference Voice Translation

Translate speech without losing your voice identity.

Translate speech while keeping a voice close to your reference voice. VoxShift outputs reference-voice translated speech for Discord, game VC, and OBS on Windows.

Real-Time Voice Translation

AI voice translation shaped for Windows voice chat.

Near-real-time AI voice translation for Windows. Translate your microphone into reference-voice speech for Discord, game VC, OBS, and meetings.

Live Translation Captions

Turn live voice into translated captions you can check.

Translate microphone or desktop audio into real-time AI subtitles for a built-in subtitle window and OBS captions. Test latency with the VoxShift free version.

Windows Voice Translator

A Windows voice translator for VC, games, and streams.

VoxShift is a Windows voice translator that combines microphone input, speech recognition, translation, reference-voice synthesis, OBS captions, and virtual audio routing.

System Audio Translator

Translate Windows system and desktop audio into live captions.

Translate Windows system and desktop audio into live captions with VoxShift. Test YouTube, calls, streams, audio routing, source limits, and latency with the free version.

Meeting Voice Translator

Bring translated voice into Zoom, Teams, and calls.

Use VoxShift with Zoom, Teams, and Google Meet through your Windows audio setup. Test translated speech, captions, latency, and routing with the free version.

Local / Privacy-first Voice Translation

Voice translation designed to stay on your PC by default.

Privacy-focused Windows voice translation. By default, VoxShift does not send audio, reference voice, captions, or translated text to operator servers.

Virtual Microphone Translator

Route translated speech into your voice chat app.

Route translated speech to Discord, game voice chat, OBS, and call apps through Windows audio setup. Test routing with the VoxShift free version.

Voice Translator for Streamers

Reach international viewers with translated voice and captions.

Use translated speech and OBS translated captions for Twitch, YouTube Live, Kick, and international streams. VoxShift is Windows voice translation software for streamers.

Microsoft Store Voice Translator

Install from Microsoft Store, then test the free trial first.

VoxShift is a Windows voice translator on Microsoft Store. Use the free trial to check GPU, VRAM, audio devices, Discord routing, and OBS captions before buying.

Soundboard Voice Translator

Translation is the core. Soundboard cues support the gaps.

VoxShift focuses on reference-voice translation, with Soundboard cues, voice polish, OBS captions, and routing checks for Discord, game VC, and streams.

Setup Wizard

The first setup wall is now guided.

VoxShift handles AI models, virtual audio, microphones, and output routes. The setup wizard walks through the checks in order, so configuration issues are easier to find before Live starts.

VoxShift setup wizard in English showing the steps for display language, quality for this PC, languages, microphone and output, voice recording, and the final check.
  1. 1Display language
  2. 2Quality for this PC
  3. 3Input / output language
  4. 4Microphone
  5. 5Translated voice output / monitor
  6. 6Record your voice (optional)
  7. 7Final check
  8. 8Start Live
Limits

Know this before purchasing

  • This is not zero-latency translation.
  • Latency and voice quality can degrade without enough GPU/VRAM.
  • The other person's speech is shown as translated subtitles, not read aloud.
  • In Ultra-low VRAM mode, translation runs on the CPU, so it can be slower.
  • Per-speaker separation is not supported.
  • If multiple people talk at once, transcription and translation accuracy may drop.
  • Translation quality varies by model, language, speech clarity, and specialized vocabulary.
  • Using another person's voice without consent is prohibited.
  • Use caution for work, medical, legal, financial, or other high-impact situations where mistranslation matters.
Pricing

Start free. Upgrade if your PC is ready.

Free version

Free

Download the free version
  • Steam Demo / Microsoft Store free trial
  • Live sessions up to 10 minutes (start again anytime)
  • Translation output: English only
  • Fixed light model set
  • Soundboard: up to 3 items
  • Setup wizard, voice recording, and device checks

Full version

Recommended

One-time purchase

Buy now
  • Reference Voice Translation
  • Live without the 10-minute limit
  • Output in all 10 languages
  • Automatic model selection for your PC
  • Optional higher-quality models
  • Bidirectional Subtitles
  • Discord / Game / OBS Output
  • OBS Captions
  • Soundboard
  • Noise / EQ / Clipping protection

The full version is sold on Steam (Early Access) and the Microsoft Store, with no subscription. Each store is a separate product and license: buying on one does not unlock the other. See each store page for the price.

Live voice translation requires an NVIDIA CUDA GPU (Turing or newer) with 4 GB VRAM or more. Please try the free version on your PC before buying.

Requirements

Check the runtime environment before purchase

Live translation with reference-voice synthesis requires an NVIDIA CUDA-capable GPU, Turing or newer (GeForce GTX 16 / RTX 20 series or later), with 4 GB VRAM or more. On Radeon, Intel GPU, or no-GPU systems, Live voice generation is unavailable. VoxShift checks your PC and picks a GPU memory mode automatically; to choose it yourself, use Performance → Manual settings. Optional higher-quality models need more VRAM.

ModeVRAMUse Cases
Setup / checksNot requiredSetup wizard, audio checks, and diagnostics, also on Radeon / Intel / no-GPU PCs
StandardFrom about 5.8 GiBPCs with enough GPU memory
Low VRAMAbout 3.8 GiBPCs with less GPU memory
Ultra-low VRAMAbout 2.4 GiBPCs with very little GPU memory; translation runs on the CPU and can be slower
Feature Details

Main features

Live Translation+
  • Microphone input
  • Voice activity detection
  • Speech recognition
  • Translation engine
  • Reference voice generation
  • Streaming playback
  • Fast / Quality modes
  • Now / History view
  • Start / stop / pause / resume
Reference Voice+
  • Short voice recording (optional)
  • Reference text to read aloud
  • Use my live voice as a reference
  • Only voice my own speech
  • Noise suppression
  • Saved voices and profiles
Bidirectional Subtitles+
  • Partner subtitles
  • Desktop audio capture
  • Process loopback
  • Source text
  • Translated text
  • Auto clear
  • Log saving
Audio Routing+
  • Input device selection
  • Translated voice output
  • Monitor (hear it yourself)
  • Passthrough of your own voice with adjustable volume
  • Virtual audio detection
  • VB-CABLE: optional install on Steam, official page guidance on Microsoft Store
Soundboard+
  • Preset reactions
  • Short cues
  • Stream sound effects
  • One-shot playback during games
  • Conversation support during translation wait
  • Optional EQ
  • VC profiles
Streaming / OBS+
  • Built-in subtitle window
  • OBS WebSocket
  • Text source update
  • Source + translation
  • Translation only display
Tuning+
  • Automatic PC check
  • GPU memory modes: Standard / Low VRAM / Ultra-low VRAM
  • Performance → Manual settings
  • Voice quality: Automatic / Standard / High
  • Optional quality recognition and voice generation models
  • Noise suppression
  • EQ presets
  • Clipping protection
Diagnostics+
  • GPU / VRAM check
  • Live start check
  • Estimated VRAM
  • Audio device diagnostics
  • Setup diagnostics report
FAQ

FAQ

Is it fully real-time?+

No. VoxShift is semi-real-time voice translation, and delay varies with your GPU, VRAM, sentence length, and settings. Fast mode starts translating before you finish the sentence.

What GPU do I need?+

Live voice translation requires an NVIDIA CUDA GPU, Turing or newer (GeForce GTX 16 / RTX 20 series or later), with 4 GB VRAM or more. When GPU memory is tight, VoxShift picks Low VRAM or Ultra-low VRAM mode automatically. On Radeon, Intel GPU, or no-GPU PCs, only setup and diagnostics are available.

What are the free version's limits?+

The Steam Demo and the Microsoft Store free trial have the same limits: each Live session stops after 10 minutes (you can start again), translation output is English only, the light model set is fixed, and the soundboard holds up to 3 items. Setup, voice recording, device checks, and the OBS link can all be tried.

Can it translate the other person's voice?+

Yes. Partner subtitles listen to the other person (call, game, or video audio) and show their speech as translated subtitles. It is not read aloud.

Can it separate multiple speakers?+

No. Overlapping speech may reduce accuracy. Turning on “Only voice my own speech” keeps other voices your mic picks up from being spoken.

Does it perfectly reproduce my voice?+

No. It aims for a voice close to yours, not a perfect copy. A short recording of you reading one sentence aloud helps it sound more like you.

Can I use someone else's voice?+

No. Voices without consent are prohibited.

Check whether your PC can run it first.

Live voice translation requires an NVIDIA CUDA GPU (Turing or newer) with 4 GB VRAM or more. Please try the free version on your PC before buying.

FreeBuy