Google has launched Gemini 3.1 Flash TTS, an advanced text-to-speech model, along with Gemini Robotics-ER 1.6, enhancing AI capabilities for developers and enterprises.
Google has announced the launch of its Gemini 3.1 Flash TTS, a new text-to-speech model that enhances sound quality, expressiveness, and offers precise control across more than 70 languages. Designed for a variety of users, including developers and enterprises, the model is accessible through the Gemini API, Google AI Studio, Vertex AI, and the Google Vids service.
This model achieved a score of 1211 in the Artificial Analysis TTS ranking, reflecting strong performance in blind audio quality tests conducted with a large number of participants. It is noted for being a cost-effective solution that produces high-quality speech synthesis, capable of generating multiple speakers' dialogues.
New Features: Audio Tags
Among its new features, the version 3.1 Flash TTS introduces audio tags, which allow users to control the style and pace of the speech. Early testers have praised the enhanced control and expressiveness this feature provides, stating that it elevates simple text to high-quality voice performances.
Gemini Robotics AI Model Launch
In addition to the TTS model, Google has unveiled the Gemini Robotics-ER 1.6, aimed at enabling robots to execute complex tasks in real-world environments by enhancing cognitive capabilities and embodied thinking. This model excels in spatial perception and action planning, showing notable improvements over earlier versions, particularly in spatial and physical reasoning tasks.
Developed with Boston Dynamics, Gemini Robotics-ER 1.6 can process data from intricate measuring devices and analyze metrics visually. During testing for security threat detection, it outperformed its predecessor by 6% in text scenarios and by 10% in video analyses.
Gemini on macOS
Google has also launched a native Gemini application for macOS, which can be accessed conveniently and includes features like sharing windows for context transfer. The app supports image generation and video creation tools, further integrating Gemini's advanced functionalities.
Earlier this year, Google released Gemma 4, a new suite of open AI models focused on advanced reasoning capabilities.
