Bilingual Subtitles for Both Sides of a Conversation
Overview
This guide sets up the Sokuji desktop app to show both sides of a conversation as translated text: what you say and what the other person says, each with its translation. Use it for bilingual captions, for following a call where everyone speaks their own language, or for a translated transcript of a meeting. No synthetic voice is generated, nothing is sent into the meeting, and you need no virtual audio cable. It uses KizunaAI (Powered by Soniox). The screenshots are from Sokuji 0.41.1 on Windows with Microsoft Teams, between 中文 and English.
1Set up Sokuji with KizunaAI
If you have not done so yet, follow the KizunaAI quick start to install Sokuji and sign in.
2Choose “Two-way online conversation, subtitles only”
In the setup guide, choose Two-way online conversation, subtitles only. It puts Sokuji in Both mode with subtitles only. If you have already finished the setup, click Both in the mode switch at the bottom left of the main window and switch on Text Only in Settings.
3Set the two languages
Set I speak to your own language and they read to the other person’s. The line underneath shows the other direction. Here: I speak 中文, they read English.
Tip
Do not leave I speak on Auto Detect. In Both mode Sokuji has to know your language to translate the other side into it, and Start stays disabled until you choose one.
4Choose your microphone and the meeting app
In Settings, under Microphone, pick your real microphone. Under Other’s audio, pick your meeting app, here Microsoft Teams. You keep using your real microphone in the meeting app too: Sokuji only listens.
Tip
If your meeting app is not in the list, join the call first (an app often appears only once it plays sound) and click the refresh icon, or choose System Audio (All Applications).
5Start translating
Click Start. Sokuji shows both sides as subtitles, each line with its translation. To let the other person read along, share the Sokuji window or open the subtitle window with Subtitle in the title bar and share that.
6Save the transcript
Click the download button in the toolbar. Under Include, choose whether to keep the original (Src) and the translation (Trans) for each side, then Copy to clipboard, Download as .txt or Download as .json. With Auto-save when session ends switched on, Sokuji saves it for you every time you stop. The options become available once there is something to save.
Tips for Best Results
- Wear headphones. Otherwise your microphone picks up the other person from your speakers, and Sokuji shows their words as yours.
- Pick the meeting app rather than System Audio, so that notification sounds and music from other programs are not translated.
- Stop the session when the meeting ends: a running session keeps using your balance.
Frequently Asked Questions
Does the other person see the subtitles?
Only if you share your screen or the subtitle window. Otherwise the subtitles appear on your computer only.
Do I need VB-CABLE for this?
No. The virtual audio cable is only needed when the other person should hear your words as a translated voice.
Can I switch to a translated voice later?
Yes. Switch off Text Only and follow the two-way meeting guide to set up the virtual audio cable.
Troubleshooting
Still stuck? Send us feedback from the account menu, or write to support@kizuna.ai. You can also ask in GitHub Discussions.