Seeking guidance on building a low-latency AI-powered simultaneous interpretation platform with glossary support

Hi everyone,

We are building a professional real-time interpretation platform for conferences and live events.

Our requirements are:

  • Very low latency (simultaneous interpretation)
  • Natural and fluent speech output
  • One-way real-time speech translation for conference audiences
  • Support for a custom glossary (customer-specific terminology)
  • Ability to update the glossary per event/session

We initially tested gemini-3.5-live-translate-preview, and the translation quality and latency are excellent. However, since it currently doesn’t support system instructions or glossary enforcement, it doesn’t meet our terminology requirements.

We then started testing gemini-3.1-flash-live-preview with reasoning and a system prompt containing our glossary. We’re right now experiencing several issues:

  • The translation is less fluent than gemini-3.5-live-translate-preview.
  • The model often waits before speaking instead of translating incrementally.
  • We experience pauses and occasional interruptions during long speech.
  • Overall, it behaves more like a conversational assistant than a simultaneous interpreter.

Our goal is to build something that behaves like a human interpreter, continuously translating while the speaker is talking.

So we’d like to ask:

  1. Is gemini-3.1-flash-live-preview the recommended model for this type of application?
  2. Are there any best practices for configuring sessions (VAD, buffering, prompting, reasoning, etc.) for simultaneous interpretation?
  3. Is there a recommended way to enforce a glossary while maintaining low latency?
  4. Is glossary support planned for gemini-3.5-live-translate-preview, or is using gemini-3.1-flash-live-preview currently the intended approach for this use case?

Any guidance on the recommended architecture or implementation patterns would be greatly appreciated.

Thank you!