Gemini 3.8 text-to-speech says hello
What happened
DeepMind unveiled Gemini 3.8, a new text‑to‑speech model that can generate natural, expressive spoken language directly from prompts, supporting multiple voices and languages. The system builds on Gemini’s multimodal foundation, allowing seamless integration of speech with text, images, and video, and aims to make conversational AI feel more human‑like. Its high‑quality audio output and low latency open up possibilities for real‑time applications like virtual assistants, audiobooks, and accessibility tools.
Why it matters
Gemini 3.8 raises the bar for AI‑driven voice generation, pushing competitors to improve realism and integration across modalities, while also prompting discussions about responsible use and deep‑fake mitigation in the industry.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from Google
Google Search gets a major upgrade with Gemini 4 HydrogenGoogle · 12 Nov 2026Introducing Gemini 4 HydrogenGoogle · 12 Nov 2026Gemini 4 HydrogenGoogle · 12 Nov 2026Gemini Decisions API: Fast, calibrated multimodal decisionsGoogle · 11 Nov 2026Try Tabletop: Customizable, collaborative spaces for groups to plan, play and do more together.Google · 11 Nov 2026This page was collected from deepmind.google and summarised automatically by AIPulsee's pipeline. See how it runs.