Sokuji

Sokuji

Real-time AI translation for multilingual conversations

60 followers

Visit website
•
•
Sokuji breaks language barriers using OpenAI's Realtime API. It translates speech instantly through GPT-4o and routes audio to video calls. Available as both a desktop app with virtual audio devices and a browser extension for Google Meet/Microsoft Teams/Zoom.
Sokuji gallery image
Sokuji gallery image
Sokuji gallery image
Sokuji gallery image
Sokuji gallery image
Sokuji gallery image
Sokuji gallery image
Free
Launch tags:
Chrome Extensions•Meetings•Artificial Intelligence
Launch Team / Built With

What do you think? …

Jiang zhuo
Maker
📌
We built Sokuji to solve a real problem: enabling seamless communication across language barriers in real-time conversations. What makes Sokuji unique is its complete audio routing solution with virtual device management that integrates directly with applications like Google Meet. Unlike other translation tools that just provide text, Sokuji delivers spoken translations through your microphone in real-time, creating a truly natural conversation flow. We're most proud of how Sokuji makes advanced AI technology accessible and practical. The application creates virtual audio devices, handles automatic routing, and provides intuitive visualizations that make the complex process of simultaneous interpretation feel effortless. Our browser extension brings the same powerful features directly to your browser without installation requirements, making real-time translation available to everyone. Whether you're in international business meetings, connecting with family abroad, or learning a new language, Sokuji removes barriers to understanding. We'd love to hear how you use Sokuji and what languages you're connecting with!

Tried it while practicing Spanish with a friend and it was actually fun 😄 One thing I noticed: it worked better with a headset mic than my laptop mic. Any audio hardware recommendations or best practices for clarity?

Jiang zhuo
Maker

@hamza_afzal_butt 
The main issue lies in the clarity of the input device and background noise.

Laptop microphones typically have a wide pickup range—often a fan-shaped area in front of the laptop—so they tend to capture more background noise.

This becomes particularly problematic when the monitoring feature is enabled and output through speakers, as the microphone may pick up the translated audio, leading to reduced accuracy.

However, using headphones for monitoring and a headset microphone can avoid this issue.


I don’t have a specific microphone recommendation, but here are a few things you can try:

  • Adjust Noise Reduction based on your environment.

  • In the Audio settings, you can disable the monitoring feature or avoid using speaker output for monitoring.

@jiang_zhuo Thank you!

Joy Wang

Sokuji delivers real-time speech translation powered by GPT-4o, making multilingual communication seamless during video calls. With both a desktop app and a browser extension for Google Meet, it’s a practical and powerful tool for global collaboration.