Google DeepMind released the Gemini 3.8 text-to-speech model, supporting over 100 languages and ranking first in benchmark tests.
Google DeepMind has released its latest text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. These models support over 100 languages, rank first in Hume AI's voice design benchmark, and hold the first and second positions, respectively, in the overall quality index. The new models allow users to generate custom character voices with precise control over accents and emotions on platforms such as Google AI Studio and the Gemini API. They also include built-in safety features, such as requiring verbal consent for voice replication and embedding SynthID watermarks in all AI-generated audio to prevent misinformation.
No AI analysis yet. Tap the "AI Analysis" button above to generate one now.
Source:Google DeepMind官方博客 · Source Link
Disclaimer: This content reflects only the author’s personal views and does not constitute any investment or financial advice. If you discover any content that violates regulations,Click to Report
24H Trending
-
1
Report: Apple is developing a screenless fitness tracker prototype, targeting Whoop, with a potential launch as early as 2028; Garmin's stock price fell by as much as 2.5% intraday.
-
2
US SEC Delays Prediction Market ETF, CFTC Partners with NHL: What's the Compliance Path for New Sectors?
-
3
Prediction Market Trading Platforms: An Overview of Four Core Platforms
-
4
Bybit Exchange In-Depth Analysis: Rankings, Services, and Compliance Overview
-
5
Delphy (DPY) Token Analysis: Prediction Market Project Status and Risk Assessment
-
6
What Are Bitcoin Futures? A Comprehensive Guide to Their Mechanics and Trading Advantages
-
7
Bitcoin Hash Rate Plunge: Causes and Impact Analysis
-
8
Crypto Exchange Fees Comparison and App Selection Guide
-
9
Central Bank Digital Currencies vs. Bitcoin: Key Differences Explained
-
10
CRV Token Analysis: Curve Finance's Core Governance Token and Its Recent Market Dynamics
Markets Today
Recommended Reading











