How to Get Real-Time Subtitles for Any App on Your Desktop

You're watching a Japanese cooking tutorial on YouTube. The chef is explaining a technique you've never seen before, and the auto-generated captions are butchering every other word. Or maybe you're in a Zoom meeting where half the team speaks Mandarin, and you're struggling to keep up. Or you're trying to follow a Spanish podcast to sharpen your listening skills, but the speech is just a little too fast.

What you need is subtitles. Not the auto-generated mess that turns "dashi stock" into "donkey stock." Real, translated subtitles in your language. Appearing on screen. In real time.

Most people reach for browser extensions first, but those only work inside the browser and usually only on one specific site. Some try Google Translate's microphone mode, but that means switching windows and losing the content you're trying to watch. What you actually want is a floating subtitle overlay that works with ANY app on your computer. Here's how to set that up in under a minute.

The old way (and why it doesn't work)

If you've tried to get subtitles for foreign-language content before, you've probably run into one or more of these dead ends:

• YouTube auto-captions: They exist, and they're free. But the accuracy is inconsistent, especially for non-English content. The built-in translation feature runs those already-shaky captions through another layer of machine translation. The result is often garbled and unreliable. Fine for getting the gist, terrible for actually understanding what's being said.
• Browser extensions: There are extensions that add subtitle overlays to specific websites. The problem? They only work in the browser, only on certain sites, and they tend to break whenever the site updates its layout. They also add bloat and can slow down your browsing. And they're completely useless for desktop apps like Zoom or Spotify.
• Google Translate mic mode: Open Google Translate, tap the microphone, and it listens. Sounds promising, but it requires you to switch away from whatever you're watching or listening to. You lose visual context entirely. It's clunky, and it wasn't designed for continuous live translation of audio streams.
• Copy-pasting into DeepL: DeepL produces excellent translations for text. But you can't paste audio into it. If you're listening to someone speak in real time, this approach simply doesn't apply.
• Professional captioning services: High quality, but expensive, slow, and complete overkill for everyday use. You're not trying to caption a documentary. You just want to understand a cooking video.

The core problem with all of these solutions is that they're app-specific. Each one only works in a single context. What you actually need is something that captures audio at the system level, so it works with every application on your machine.

The better way: system-level audio capture

Instead of building separate extensions and plugins for every app, there's a simpler approach: capture ALL audio playing on your computer at the operating system level. This means every app that produces sound becomes translatable. Zoom, YouTube, Spotify, Netflix, VLC, Discord, games, voice memos, lecture recordings. Literally anything that makes sound on your machine.

Seagull does exactly this. It's a desktop app that sits in the background, captures your system audio, runs it through real-time speech recognition and translation, and displays the result as a floating subtitle overlay. The overlay stays on top of all your windows, so you can keep watching or working while the subtitles appear.

One tool. Every app. No extensions, no plugins, no copy-pasting. If you can hear it on your computer, Seagull can translate it.

Step by step: setting up real-time subtitles

The entire setup takes less than a minute. Here's how:

Use case tips

YouTube and streaming

Just play the video normally. Position Seagull's overlay at the bottom of the video player for a natural subtitle experience. This works with YouTube, Netflix, Crunchyroll, Disney+, Twitch, or any streaming site. Since Seagull captures system audio, it doesn't matter what site or app you're using. Play the video, and the subtitles appear.

Zoom, Teams, and Google Meet

Start your meeting normally, then start Seagull. No plugins to install in the meeting app. No browser extensions. No meeting bot that joins and makes everyone uncomfortable. Seagull captures the meeting audio directly from your system's audio output. It works with Zoom, Microsoft Teams, Google Meet, Webex, and any other video calling application.

Podcasts

Listen to foreign-language podcasts with live translated subtitles. This is incredibly useful for language learners because you hear the original audio and read the translation at the same time. Your brain makes connections between the sounds and their meanings. It works with Spotify, Apple Podcasts, Pocket Casts, Overcast, or any podcast player you prefer.

Lectures and courses

Follow lectures delivered in other languages without missing a beat. This is perfect for international students attending classes taught in a language they're still learning, or for anyone taking courses on platforms like Coursera, edX, MIT OpenCourseWare, or university live streams. The subtitles help you keep up even when the professor speaks quickly.

Movies and TV shows

Watch foreign films with instant subtitles. Don't wait for official subtitle files that might take weeks to appear, or might never come at all. Play the movie in any media player, whether that's VLC, IINA, MPV, or a streaming service, and let Seagull handle the translation. Great for film buffs who want to explore cinema from around the world.