In today's globalized world, language barriers remain one of the biggest obstacles to effective communication. Youdao Translate's simultaneous subtitle translation feature is designed to break down these barriers — it captures spoken audio in real time, recognizes the speech, and instantly displays translated subtitles on your screen. Whether you're attending an international business meeting, taking an online course in a foreign language, or watching foreign-language videos, this feature ensures you never miss a word. This comprehensive guide covers everything from basic setup to advanced optimization techniques.
Youdao's subtitle translation is powered by the company's proprietary Automatic Speech Recognition (ASR) engine combined with an AI neural machine translation system. Speech recognition accuracy reaches over 97% in quiet environments, supporting real-time recognition and translation for major languages including Chinese, English, Japanese, and Korean. The 2026 version integrates Youdao's Ziyue large language model, reducing translation latency to under 0.5 seconds — virtually indistinguishable from human simultaneous interpretation. The feature is available on both desktop and mobile platforms, covering every possible use case.
How to Use Subtitle Translation
Getting started with Youdao's simultaneous subtitle feature is straightforward on both mobile and desktop platforms.
Mobile Setup
Open Youdao Translate App
Launch the Youdao Translate app on your phone and ensure it's updated to the latest version. If not installed, visit our download page to get the latest version.
Enter Subtitle Mode
Tap the "Live Subtitle" button on the home screen (or find it in the function menu). Select the source language and target language. Grant microphone permissions on first use.
Start Real-Time Translation
Tap "Start" and place your phone near the audio source. The system will automatically recognize speech and display bilingual subtitles (original and translated) on screen in real time.
Save Translation Records
Tap "Stop" when finished. The system automatically generates a complete translation transcript that you can export as a text file or share with others.
Desktop Setup (Windows & macOS)
Using Youdao Translate's subtitle feature on the desktop client is equally simple and offers additional audio input options:
- Open the Youdao Translate desktop application and click the "Live Subtitle" icon in the top toolbar
- In the settings panel, select your audio input source (microphone or system audio) and configure source and target languages
- To translate video or audio playing on your computer, select "System Audio" mode to capture screen audio directly
- Click "Start Translation" — the subtitle window appears as a floating overlay above other windows without interfering with your workflow
- Freely drag the subtitle window to reposition it, and adjust font size and transparency to your preference
Use Cases & Scenarios
The simultaneous subtitle feature adapts to a wide range of real-time translation scenarios:
Business Meetings
Real-time translation during in-person or video conferences with multi-speaker support
Online Classes
Generate bilingual subtitles while watching foreign language courses and academic lectures
Video Subtitles
Add real-time translated subtitles to YouTube, Netflix, and other streaming platforms
Live Events
Translate live speeches, exhibitions, and presentations in real time on your device
Advanced Settings & Optimization
Youdao Translate offers extensive customization options to optimize your simultaneous translation experience.
Audio Input Configuration
On desktop, you can choose from three audio input modes: Microphone Mode (ideal for face-to-face meetings), System Audio Mode (perfect for translating video/audio playing on your computer), and Hybrid Mode (captures both microphone and system audio simultaneously, ideal for video conference scenarios). On mobile, the default microphone is used for audio capture. For best results, use the feature in a quiet environment or wear headphones to minimize echo interference. External microphones can significantly improve recognition accuracy in noisy settings.
Subtitle Display Customization
Customize how subtitles appear on screen: choose to display only the translation, only the original text, or bilingual side-by-side subtitles. Font size adjusts from 12px to 36px, and window transparency is fully configurable. For extended sessions, we recommend a dark background with white text to reduce eye strain. The subtitle window supports "Always on Top" and "Click-Through" modes, allowing it to float above any application without interfering with mouse interactions. You can also set the maximum number of subtitle lines displayed simultaneously and configure auto-scroll behavior.
Custom Terminology
For industry-specific translation needs, Youdao supports importing custom terminology databases. Prepare a CSV file with your specialized terms and their translations, then import it into the app. During simultaneous translation, the system prioritizes terminology database matches, ensuring professional terms are translated consistently and accurately. This is particularly valuable for medical conferences, legal forums, tech summits, and other specialized events where standard translation might miss domain-specific terminology.
Tips for Best Results
- Minimize Background Noise: Use in quiet environments whenever possible. Background noise significantly impacts speech recognition accuracy. External microphones deliver noticeably better results than built-in ones
- Stable Network Connection: Live subtitle translation requires continuous internet connectivity for real-time ASR and translation. Use stable Wi-Fi or 4G/5G networks and avoid areas with frequent disconnections
- Pre-set Languages: Manually select source and target languages instead of relying on auto-detection to minimize latency. Fixed language pairs yield faster and more consistent translations
- Volume Control: Ensure the audio source volume is within an appropriate range — too quiet makes recognition difficult, while excessive volume may cause distortion that affects accuracy
- Export Promptly: Save your translation transcripts immediately after each session. Export options include TXT, SRT subtitle format, and Word documents for easy review and archiving