Gemini 3.1 Flash Live: Google’s latest AI audio model

kept by eddie mar 27

Google released Gemini 3.1 Flash Live, its highest-quality audio model, for real-time dialogue across developer, enterprise, and consumer products.

Gemini 3.1 Flash TTS: New text-to-speech AI model
Gemini 3.1 Flash TTS introduces audio tags for granular control over vocal style and pacing in over 70 languages, delivering top-quality, watermarked speech generation.
also on SynthID, Google AI Studio, Google, #generative-ai, #ai, #developer-tools
Nano Banana Pro
Hacker News commenters critique Google's Nano Banana Pro image model for vague rollout, SynthID watermark removability, and unreliable text and diagram generation.
also on SynthID, Google, #generative-ai, #ai, #developer-tools
GitHub - RunanywhereAI/RCLI: Talk to your Mac, query your docs, no cloud required. On-device voice AI + RAG
RCLI is an open-source, on-device voice AI for macOS that runs STT, LLM, TTS, and VLM entirely locally on Apple Silicon, with sub-200ms latency and no cloud dependency.
also on #voice-ai, #ai, #developer-tools
Real-time Voice AI. Built to Scale.
Smallest AI argues that specialized small models operating on compressed representations, rather than monolithic large models, are the future of real-time voice AI.
also on #voice-ai, #ai
Google tests voice cloning on AI Studio powered by Gemini
Google is testing voice cloning via a hidden UI option and GitHub repository import for AI Studio, hinting at upcoming native audio and developer tools.
also on Google AI Studio, Google, #generative-ai, #ai-integration, #ai, #developer-tools