🛠 Google Unveils Gemini 3.5 Live Translate
The new audio model provides real-time streaming speech translation with minimal latency. The system supports over 70 languages and preserves natural intonation and voice tempo.
🌍 The transition to continuous stream translation reduces barriers in international communications. Integration with LiveKit, Agora, and Pipecat simplifies the implementation of SOTA solutions into existing platforms.
👤 The technology allows a smartphone to be used as a personal simultaneous interpreter that understands not just words, but also emotions.
Source 1: https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-live-3-5-translate/