Unitra AI
Unitra AI is a desktop application that provides real-time translation for voice chat, typed chat, and on-screen text in PC games. It captures microphone and desktop audio simultaneously, runs speech recognition locally, and delivers translated subtitles in about one second through a click-through overlay. The app supports 35 languages and includes gaming-specific terminology for over 12 titles, with a privacy-first design that keeps audio on-device by default.
- Gaming & eSports
- Artificial Intelligence
- Applications
- Software Only
- AI Agents
Funding
Founders
Founder details are not available yet.
Product
Problem
Language barriers in online gaming prevent players from coordinating with teammates, streaming to international audiences, or engaging with players who speak different languages. Existing translation tools are not designed for real-time gameplay, requiring alt-tabbing, copy-pasting, or interrupting the action, which disrupts immersion and slows communication.
Solution
Unitra AI is a desktop app that translates game-related audio and text in real time, capturing both microphone and desktop audio simultaneously. It runs speech recognition locally on the device and sends the text to a cloud translation pipeline optimized for gaming vocabulary, delivering translated subtitles in about one second. Translations appear in a non-intrusive, click-through overlay that auto-detects the active game, so players never have to leave the action. The app also supports text and screen translation for chat messages and on-screen UI text, including automatic translation of a selected screen area that updates as text changes. With Voice Output, Unitra AI translates what a player says and speaks it through a virtual microphone into game voice chat or Discord, letting teammates hear in their own language. Audio privacy is a core feature: all audio processing stays on-device by default, with no uploads or recordings unless the user explicitly opts in.
Target Audience
Primary users are gamers who play with international teammates or stream to multilingual audiences, along with remote teams needing cross-language meeting support and language learners seeking immersive real-time translation.
Features
- Real-time voice translation with ~1 second end-to-end latency, combining on-device ASR with a cloud translation pipeline
- Dual audio source capture for simultaneous microphone and desktop audio, covering game voice chat, Discord calls, and meeting audio
- Click-through, always-on-top overlay with automatic game detection, plus a free Xbox Game Bar widget for exclusive fullscreen games
- Gaming-specific terminology engine that recognizes characters, items, abilities, and callouts unique to each title, with >90% accuracy across 12+ games and 35 supported languages
- Privacy-first architecture: audio stays on-device by default, with no uploads, collection, or storage unless the user opts in
- Automatic screen translation: pick a chat box or screen area once and every new line is translated as it appears, with no game process hooking, DirectX/OpenGL injection, or memory access
- Voice-to-voice output that speaks translations through a virtual microphone in 10 languages, audible to teammates in game voice chat or Discord
- Custom Vocabulary for names and in-game terms on paid tiers, plus recognition of up to 3 languages simultaneously