Real-time speech translation service for live events and multilingual audiences
Use Gemini 3.5 Live Translate to let an audience listen to a speaker in their own preferred language in near real time — the speaker talks normally, the model detects the source language automatically and streams translated audio to each listener in their chosen language.
online BOTH AI Agents & Automation
From AI Engineer — Can Your Agent Hear You Now? Building Live Voice Agents with Gemini — Thor Schaeff
Problem: International audiences need live interpretation, and conventional translation pipelines are not near real time or conversational — the model translates as soon as it recognizes the context of the speech.
For: Conferences, international events and multilingual audiences who cannot all understand the speaker's language.
Products from this video
Gemini 3.5 Live Translate Gemini Live API Gemini TTS Google AI Studio Interactions API LiveKit Omni Flash Pipecat
Examples
- The talk itself was streamed to attendees in their preferred language via a QR code, with attendees confirming audio in German and Chinese.
Other takes on AI agent platforms and compute access
- Autonomous AI agents that perform administrative labor for underserved small businesses, starting with dental practices
- A personal, open-source AI agent that can be operated through messaging channels such as WhatsApp and Discord
- Enterprise AI concierge for customer, sales, and operational workflows
- AI appointment-scheduling assistant for healthcare providers
- Autonomous SEC-filing research desk with self-graded scorecards
- Production-ready inference hosting for open AI models