4 Interpretation Modes for Every Situation
From lectures to meetings, conversations to simultaneous interpretation — one platform covers every language challenge.
What is AI Real-time Interpretation?
AI real-time interpretation is the technology that instantly recognizes speech and translates it into another language, delivering output as subtitles or voice. InterLive uses this technology to offer 4 interpretation modes that enable multilingual communication without a professional interpreter.
Mode Comparison
| 모드 | Direction | Token rate | Best for |
|---|---|---|---|
| One-way | 1 token/min | Lectures, presentations, in-person meetings | |
| Two-way | 1 token/min | Negotiations, consultations, casual conversation | |
| Simultaneous two-way | 2 tokens/min | In-person negotiations, interviews, contract meetings | |
| One-way (many-to-many) | 1.5 tokens/min | Video conferences, international conferences, webinars |
In-person
Start interpreting with one microphone button. Perfect for lectures, presentations and 1:1 meetings.
Conversation
Press to speak, release to hear — walkie-talkie style for natural two-way conversation.
Face-to-face
Place one device between two people, each speaking their own language. Two sessions run simultaneously.
Meeting
Paste a meeting URL → bot joins → subtitle link posted in chat. Supports Zoom, Teams, Meet and Webex.
Frequently Asked Questions
What is AI simultaneous interpretation?
AI simultaneous interpretation is technology that translates and outputs speech into another language almost simultaneously as the speaker talks. InterLive uses GPT-based AI to provide real-time interpretation across 15 languages.
Which mode uses the fewest tokens?
In-person and Conversation modes are the most efficient at 1 token per minute. The meeting bot uses 1.5 tokens/min. Face-to-face (simultaneous two-way) uses 2 tokens/min.
How do I get real-time interpretation in a Zoom meeting?
In InterLive's Meeting mode, enter your Zoom meeting URL and a bot joins automatically. The bot shares a subtitle link in the meeting chat, which participants can open without logging in to see real-time captions.
Is voice output (TTS) supported?
Yes. In all interpretation modes you can enable AI voice synthesis (TTS) to hear the translation spoken aloud — like having a live AI interpreter beside you.