Our latest audio model, Gemini 3.5 Live Translate, takes real-time speech translation to the next le...
TL;DR · AI Summary
Google 推出 Gemini 3.5 Live Translate，支持 70 多种语言的实时低延迟语音翻译。
Key Takeaways
- Gemini 3.5 Live Translate 支持 70 多种语言的实时低延迟翻译。
- 模型可自动检测语言并即时开始翻译，无需手动调整设置。
- 具备噪声过滤功能，可在嘈杂环境中提供更清晰的语音翻译。
Outline
Jump quickly between sections.
- §引言
Google 推出 Gemini 3.5 Live Translate，支持 70 多种语言的实时低延迟语音翻译。
- ·核心功能
Gemini 3.5 Live Translate 支持多语言输入、自动语言检测和噪声过滤。
- ›技术亮点
模型能够实时处理语音输入，生成更自然的语音输出，同时具备噪声过滤能力。
Mindmap
See how the topics connect at a glance.
查看大纲文本（无障碍 / 无 JS 友好）
- Gemini 3.5 Live Translate
- 核心功能
- 多语言支持
- 自动语言检测
- 噪声过滤
- 技术亮点
- 实时低延迟翻译
- 自然语音输出
Highlights
Key sentences worth saving and sharing.
Gemini 3.5 Live Translate 支持 70 多种语言的实时低延迟翻译。
模型可自动检测语言并即时开始翻译，无需手动调整设置。
具备噪声过滤功能，可在嘈杂环境中提供更清晰的语音翻译。
Google AI Developers on X: "Our latest audio model, Gemini 3.5 Live Translate, takes real-time speech translation to the next level for developers by delivering low-latency translation across 70+ languages. By processing speech as it streams in near real time, the model enables devs to build low-latency https://t.co/TYypC6g1Hg" / X
Google AI Developers
@googleaidevs
Our latest audio model, Gemini 3.5 Live Translate, takes real-time speech translation to the next level for developers by delivering low-latency translation across 70+ languages. By processing speech as it streams in near real time, the model enables devs to build low-latency
— Multilingual input: Understands multiple languages in a single session without needing to adjust settings. — Auto-detection: Identifies the spoken language and begins translation instantly. — Native audio processing: Generates more natural-sounding speech that preserves speakers' intonation, pacing, and pitch. — Noise robustness: Filters out ambient noise for clearer conversation in loud environments.
00:00
3:23 PM · Jun 9, 2026
31.8K
Views
1
3
13
2
5
25
8
182
33
Read 13 replies