PulseAugur
实时 19:47:00
English(EN) Fluid, natural voice translation with Gemini 3.5 Live Translate

Google 推出 Gemini 3.5 Live Translate 实现实时语音翻译

Google 推出了 Gemini 3.5 Live Translate,这是一款先进的音频模型,专为实时语音到语音翻译而设计。该新模型支持 70 多种语言,旨在通过保留原始说话者的语调和节奏来提供流畅自然的翻译。与传统系统不同,它进行连续翻译,最大限度地减少停顿并与说话者保持紧密同步。该技术正在集成到各种 Google 产品中,包括 Google MeetGoogle Translate 应用,并且还可以通过 API 提供给开发者。 AI

影响 加速实时跨语言交流,可能降低全球商业和人际交往的壁垒。

排序理由 这是来自前沿实验室(Google DeepMind)的新模型发布,具有特定的名称和版本。

在 Google DeepMind 阅读 →

AI 生成摘要 · Google Gemini · 来自 8 个来源。 我们如何撰写摘要 →

Google 推出 Gemini 3.5 Live Translate 实现实时语音翻译

报道来源 [8]

  1. X — Google AI TIER_1 English(EN) · GoogleAI ·

    Today, we released Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation.

    Today, we released Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation. It supports over 70 languages and starts translating as soon as you start talking, streaming translations while listening to what you say next. No awkward pauses or choppy…

  2. Google DeepMind TIER_1 English(EN) ·

    Fluid, natural voice translation with Gemini 3.5 Live Translate

    Gemini 3.5 Live Translate brings near real-time, natural speech translation to Google AI Studio, Google Translate and Google Meet.

  3. The Decoder TIER_1 English(EN) · Matthias Bastian ·

    Google's Gemini 3.5 Live Translate delivers real-time voice translation across 70+ languages

    <p><img alt="" class="attachment-full size-full wp-post-image" height="768" src="https://the-decoder.com/wp-content/uploads/2026/04/google_gemini_optical_trick.png" style="height: auto; margin-bottom: 10px;" width="1376" /></p> <p> Google releases Gemini 3.5 Live Translate, an au…

  4. Ars Technica — AI TIER_1 English(EN) · Ryan Whitwam ·

    Google announces Gemini 3.5 Live Translate for instant voice-to-voice translation

    Voice translations preserve speaker's tone, pacing, pitch—with SynthID watermarks for security.

  5. MarkTechPost TIER_1 English(EN) · Asif Razzaq ·

    Google Releases Gemini 3.5 Live Translate, a Streaming Speech-to-Speech Audio Model Covering 70+ Languages Across Meet, Translate, and the Live API

    <p>Gemini 3.5 Live Translate streams speech-to-speech translation across 70+ languages. It generates audio continuously, staying a few seconds behind the speaker. The model reaches developers via the Gemini Live API, plus Google Meet and the Translate app.</p> <p>The post <a href…

  6. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Google has released Gemini 3.5 Live Translate, a streaming speech-to-speech audio model covering over 70 languages. The model preserves speaker intonation and p

    Google has released Gemini 3.5 Live Translate, a streaming speech-to-speech audio model covering over 70 languages. The model preserves speaker intonation and pacing while translating in real-time across Google Meet, Translate app, and the Live API. It is rolling out for enterpri…

  7. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Google's new Gemini 3.5 Live Translate audio model supports near real-time speech-to-speech translation in over 70 languages. It's available in the Google Trans

    Google's new Gemini 3.5 Live Translate audio model supports near real-time speech-to-speech translation in over 70 languages. It's available in the Google Translate mobile app, and it's coming soon to Google Meet https://www. thurrott.com/a-i/337167/new-ge mini-3-5-live-translate…

  8. Mastodon — mastodon.social TIER_1 English(EN) · [email protected] ·

    Google announces Gemini 3.5 Live Translate for instant voice-to-voice translation https://arstechnica.com/ai/2026/06/google-announces-gemini-3-5-live-translate-

    Google announces Gemini 3.5 Live Translate for instant voice-to-voice translation https://arstechnica.com/ai/2026/06/google-announces-gemini-3-5-live-translate-for-instant-voice-to-voice-translation/ # AI # Tech # Translation