Gemini 3.1 Flash Live: Making audio AI more natural and reliable | Endigest
Deepmind
Get the latest tech trends every morning
Receive daily AI-curated summaries of engineering articles from top tech companies worldwide.
Google introduces Gemini 3.1 Flash Live, its highest-quality real-time audio and voice model for natural dialogue.
- •Scores 90.8% on ComplexFuncBench Audio for multi-step function calling, outperforming the previous model
- •Leads Scale AI's Audio MultiChallenge with 36.1% score (thinking mode on), testing complex instruction following in real-world audio conditions
- •Improved tonal understanding recognizes acoustic nuances like pitch and pace, dynamically adjusting to user frustration or confusion
- •Available via Gemini Live API (developer preview), Gemini Enterprise for Customer Experience, Search Live, and Gemini Live
- •Search Live expands to 200+ countries with multilingual support; all audio watermarked with SynthID to prevent misinformation
This summary was automatically generated by AI based on the original article and may not be fully accurate.
Google Cloud
Databricks
Stripe