Gemini 3.8 text-to-speech says hello
The capability lets AI systems communicate with users through spoken words, expanding accessibility beyond text-based interfaces.
Get smart on it
Google DeepMind has introduced two new text-to-speech models that allow creators and developers to generate expressive synthetic voices with detailed control over character design, delivery, and performance. The models enable users to create custom voices from natural language descriptions, replicate voices from audio samples, and direct line-by-line vocal delivery across applications like podcasts, audiobooks, and interactive media. These tools include safeguards such as consent verification for voice replication and watermarking to detect AI-generated speech. The models are available through Google AI Studio, the Gemini API, and other Google products, supporting over 100 languages and regional dialects.
Related news
A Coding Guide to TypeSafe AI Jev: Typed Decisions, Calibrated Confidence, and Speculative Fan-Out with a System One Model
In this tutorial, we work with Jev, TypeSafe AI’s first System One model, which does not generate text at all: we send it a piece of program state and a set of typed questions, and it returns choices, scores, and yes/no probabilities that our code can branch on directly. We install the official Python SDK, make a first call that uses all three question primitives at once, and look at how the shape of the state changes what the model can know. We then recompute the published confidence sta
NVIDIA Releases Nemotron 3 Diarization: A 100M-Parameter Open-Weight Model That Tracks 8 Speakers in Real Time
NVIDIA has released Nemotron 3 Diarization, an open-weight speaker diarization model on Hugging Face. It answers one question about any conversation: who spoke when. The 100M-parameter model tracks up to 8 speakers, including when voices overlap. One checkpoint handles both offline recordings and real-time streaming. Is it deployable? Yes. The weights are released under the OpenMDW License 1.1, which permits commercial use. It runs on Linux through NVIDIA NeMo, using Ampere, Ada Lovelace, Ho
