--- title: "Speech-to-Speech Translation on Windows — Hear, Don't Read" description: "What speech-to-speech translation is, why hearing beats reading, and how VoxisLive runs an interpreter model live on any audio playing on Windows." url: https://voxislive.com/speech-to-speech-translation language: "en" source_html: https://voxislive.com/speech-to-speech-translation site: "Voxis — real-time voice translation" og_image: https://voxislive.com/assets/og.png generated_by: voxislive-markdown-pipeline --- [Home](https://voxislive.com/) · / · Speech-to-speech translation SPEECH-TO-SPEECH # Hear the translation. Don't read it. VoxisLive is a speech-to-speech translation app for Windows and Linux: it listens to the spoken audio your PC plays — a video, a game, a meeting — and speaks the translation back in a natural voice, in real time. ## What is speech-to-speech translation? Speech-to-speech translation — sometimes called spoken translation or **S2ST** — takes audio in one language and returns audio in another. The input is a voice; the output is also a voice. That is the crucial difference from the translation most people know, where you type text and read the result, or a video shows a line of subtitles to scan. A complete S2ST pipeline does three things: recognizes the spoken words, translates their meaning, and synthesizes a new voice that says them aloud. VoxisLive runs this chain continuously, so the result lands in your ears a few seconds after the original speaker — close enough to follow a conversation, a lecture or a scene as it happens. Your eyes stay on the gameplay, the slides, or the person talking. ## Why hearing beats reading Subtitles work, but they cost you something: pulling your gaze to the bottom of the screen, parsing text, snapping back — many times a minute. In a fast scene you miss the visuals; in a game you miss the moment; in a meeting you stop watching the speaker. Reading is a second task layered on top of watching. Spoken translation removes that task. The language you understand simply arrives through your speakers while everything you see stays in front of you — the same reason live events use interpreters speaking into an earpiece rather than scrolling a transcript on a wall. Captions still exist if you want them: export a TXT, SRT or VTT transcript after any session. They're a record, not the thing you rely on in the moment. ## A native simultaneous interpreter VoxisLive captures system audio with Windows WASAPI process-loopback — no virtual cable, no extra driver, no bot in your call — and excludes its own output so it never translates the voice it just produced. On Linux it does the same without a driver: VoxisLive creates its own PipeWire virtual sink on demand and routes the app you are translating into it. Install it from the Snap Store with `sudo snap install voxis` — the Snap Store serves the current published build. The captured speech goes to a **native simultaneous interpreter model**: rather than waiting for a sentence to finish, it begins translating while the speaker is still talking and stays a few seconds behind — exactly how a human interpreter works in a conference booth. That short, steady lag is what makes the output feel live instead of stop-and-start. ## Two modes In **Video / Game mode** translation is one-way: the other voice comes into your language and the original audio is ducked so the spoken translation sits clearly on top. In **Meeting mode** it is two-way: the other party is translated into your language, and your own speech is translated into theirs and fed into a virtual microphone — with no bot in the participant list. VoxisLive runs on Windows 10 and 11 and on Linux, and speaks 79 target languages. Get it on the [Microsoft Store](https://apps.microsoft.com/store/detail/9P5Z0KVS58RS?cid=DevShareMCLPCB), or use the paid Bring Your Own Key unlock inside the app with your own Gemini or Qwen key — see [GitHub](https://github.com/VoxisLive/voxislive) for how it works. FAQ ## Common questions ### What is a speech-to-speech translation app? A speech-to-speech translation app listens to spoken audio in one language and produces spoken audio in another. Instead of showing you text to read, it speaks the translation aloud in a natural voice. ### How is spoken translation different from subtitles? Subtitles give you text to read while also watching the screen, splitting your attention. Spoken translation delivers the meaning straight to your ears, so your eyes stay on the video, game or speaker. ### Does VoxisLive translate as the speaker talks? Yes. It uses a native simultaneous interpreter model that begins translating while the speaker is still talking, staying a few seconds behind rather than waiting for full sentences. ### How many languages can it speak? 79 target languages. You pick the language in the app and the translation is spoken back in that language. ### How much latency does VoxisLive add? A few seconds. A spoken translation can't be instant — the model has to hear enough of a sentence to translate it correctly — but VoxisLive's native simultaneous interpreter starts speaking well before the source sentence ends, rather than waiting for a full pause. ## Keep reading [Voice translation vs subtitles · There are two ways to understand foreign-language audio: read a translation as text, or hear a translation spoken…](https://voxislive.com/voice-translation-vs-subtitles) · [Live AI dubbing · Live AI dubbing translates and re-speaks audio the moment it plays — not after the fact.](https://voxislive.com/live-dubbing) · [Languages · VoxisLive translates 79 languages in real time. Paid plans speak all 79; the free tier speaks 35 and shows live…](https://voxislive.com/languages) Free to start · 10 free minutes every day ## Hear every language, in real time. Runs on Windows 10 and 11 and on Linux — driverless capture, no setup ritual, no bot in your call. [Get it on Microsoft Store](https://apps.microsoft.com/store/detail/9P5Z0KVS58RS?cid=DevShareMCLPCB) [Linux · Snap Store](https://snapcraft.io/voxis) [View on GitHub](https://github.com/VoxisLive/voxislive) ## Structured data (JSON-LD) ```json { "@context": "https://schema.org", "@graph": [ { "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://voxislive.com/" }, { "@type": "ListItem", "position": 2, "name": "Speech-to-speech translation", "item": "https://voxislive.com/speech-to-speech-translation" } ] }, { "@type": "WebPage", "name": "Speech-to-Speech Translation on Windows — Hear, Don't Read", "url": "https://voxislive.com/speech-to-speech-translation", "description": "What speech-to-speech translation is, why hearing beats reading, and how VoxisLive runs an interpreter model live on any audio playing on Windows.", "inLanguage": "en", "dateModified": "2026-08-15", "isPartOf": { "@type": "WebSite", "name": "VoxisLive", "url": "https://voxislive.com/" } }, { "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "What is a speech-to-speech translation app?", "acceptedAnswer": { "@type": "Answer", "text": "A speech-to-speech translation app listens to spoken audio in one language and produces spoken audio in another. Instead of showing you text to read, it speaks the translation aloud in a natural voice." } }, { "@type": "Question", "name": "How is spoken translation different from subtitles?", "acceptedAnswer": { "@type": "Answer", "text": "Subtitles give you text to read while also watching the screen, splitting your attention. Spoken translation delivers the meaning straight to your ears, so your eyes stay on the video, game or speaker." } }, { "@type": "Question", "name": "Does VoxisLive translate as the speaker talks?", "acceptedAnswer": { "@type": "Answer", "text": "Yes. It uses a native simultaneous interpreter model that begins translating while the speaker is still talking, staying a few seconds behind rather than waiting for full sentences." } }, { "@type": "Question", "name": "How many languages can it speak?", "acceptedAnswer": { "@type": "Answer", "text": "79 target languages. You pick the language in the app and the translation is spoken back in that language." } }, { "@type": "Question", "name": "How much latency does VoxisLive add?", "acceptedAnswer": { "@type": "Answer", "text": "A few seconds. A spoken translation can't be instant — the model has to hear enough of a sentence to translate it correctly — but VoxisLive's native simultaneous interpreter starts speaking well before the source sentence ends, rather than waiting for a full pause." } } ] } ] } ```