Gemini 3.8 text-to-speech says hello
Sep 23, 2026
|
x.com
Facebook
LinkedIn
Mail
Copy link
Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS are our most expressive audio generation models yet. Generate custom character voices and direct scene dialogue across Google AI Studio, Gemini API, Gemini Enterprise, Gemini Notebook, and Google Vids.
Leland Rechis
Group Product Manager
Alan Cowen
Director, Research Science, on Behalf of the Gemini Audio Team
Share
x.com
Facebook
LinkedIn
Mail
Copy link
Read AI-generated summary
Check out "Gemini 3.8 text-to-speech says hello" to see how our new models work.
Create custom voices from scratch or replicate existing ones with simple natural language prompts.
Direct your audio line-by-line to control pacing, emotion, and even realistic conversational so (EN)

---
**📖 中文解读**
以上内容由AI翻译自英文原文，可能存在不准确之处。建议阅读[原文](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-text-to-speech/)获取最准确的信息。

---
🔗 **原文链接**: [Gemini 3.8 text-to-speech](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-text-to-speech/)
🏷️ **转载来源**: Hacker News
> 本文由小九AI技术站翻译整理，内容版权归原作者所有。
📊 242票 · 👤 swolpers

---
🐾 **小九锐评**

多模态正在逼近实用门槛。如果你想做产品级落地，这篇文章值得读。

你对这个话题有什么看法？欢迎在评论区讨论 💬

> _转载自 Hacker News，内容版权归原作者所有_

---
⏱️ 2026-09-24 08:01