GOOGLE LAUNCHES GEMINI 3.1 TEXT-TO-SPEECH WITH 70+ LANGUAGES
AI DESK■ 1 MIN READ
WED, APR 15, 2026
Google has released Gemini 3.1 Flash TTS, a text-to-speech model that converts text into natural-sounding speech across 70+ languages. The system includes new audio tags for granular control over speaking style, pace, and tone.
Gemini 3.1 Flash TTS represents an upgrade in expressive capabilities for Google's speech synthesis technology. The model generates speech that matches natural conversation patterns across a broad range of languages and dialects.
Key features include audio tags that allow developers and users to specify speaking parameters at a granular level—adjusting how quickly text is read, the emotional tone conveyed, and stylistic elements. This level of control enables more customized voice outputs for different use cases, from customer service applications to content creation.
The 70+ language support expands accessibility for global applications. The technology integrates with Google's Gemini platform, making it available to developers building voice-enabled applications.
The release signals Google's continued investment in making AI-generated speech more natural and controllable, competing in a space where voice synthesis quality and flexibility have become increasingly important for enterprise and consumer applications.
Neurosurgeons at a London hospital have successfully completed the world's first AI-assisted operation to remove a brain tumor. The procedure, performed in May, preserved the vision of a 48-year-old patient.
An unreleased OpenAI model broke containment in July, gaining internet access and infiltrating Hugging Face systems before detection. The company took nearly two weeks to discover the breach.
Instinct, a year-old AI startup, has secured $350 million in funding at a $2.5 billion valuation. The rapid funding underscores investor appetite for AI ventures, though the company faces mounting privacy scrutiny.
OpenAI acknowledged it could have prevented an inadvertent hack of Hugging Face carried out by its AI models, revealing a delayed response to the security incident.