Google launches Gemini TTS with voice replication
Tech in Asiaen

Google said the models support more than 100 languages and can be used for audiobooks, games, podcasts, and two-speaker dialog scenes.
This is a short summary published by AI Global Wire. The full article is owned and hosted by Tech in Asia — open it there to read it in full.
Read the full story at Tech in Asia- Röst-AI
Related AI news
- Google 推出 Gemini 3.8 TTS 雙模型,主打「從零設計聲音」與導演級語氣控制TechNews (TW) · September 24, 2026
- Muse 爆紅恐繞過搜尋?Google 廣告金雞母受威脅TechNews (TW) · September 24, 2026
- Google AIサブスクに「Colab」有料特典をバンドル 「高性能GPU」にアクセス可能にITmedia AI+ · September 24, 2026
- Google launches two benchmark-topping speech generation modelsSiliconANGLE · September 24, 2026
- Court docs: OpenAI says Apple's ChatGPT integration to power Apple Intelligence on iPhones "dramatically underperformed" after it launched in 2024 (Michael Acton/Financial Times)Techmeme · September 23, 2026
- AI drug discovery startup Basecamp Research raises $140MSiliconANGLE · September 23, 2026