Gemini 3.5 Live Translate adds natural fluency to multilingual voice conversations
Google DeepMind unveiled Gemini 3.5 Live Translate, a new real-time voice translation feature that preserves speaker tone, speech patterns, and natural fluency across language boundaries. The model processes audio streams with minimal latency, enabling natural cross-language conversation without pauses.
The capability addresses a longstanding gap in multilingual AI experiences, where previous systems often produced awkward or overly formal translations that broke conversational flow. Enterprise adoption is likely in customer service, global sales, and cross-border collaboration scenarios.