PulseAugur
实时 13:03:46

Google DeepMind launches Gemini 3.1 Flash TTS, Live, and Lite models

Google DeepMind has unveiled a suite of Gemini 3.1 Flash models, including Flash TTS for advanced text-to-speech, Flash Live for real-time dialogue, and Flash-Lite for cost-efficient, high-volume workloads. These models offer improved naturalness, expressivity, and speed, with Flash TTS achieving a high Elo score on a speech quality benchmark and Flash Live demonstrating strong performance in complex task completion. All audio generated by the TTS and Live models is watermarked with SynthID to combat misinformation. AI

排序理由 Google DeepMind released multiple new Gemini 3.1 Flash models, representing an expansion of their frontier intelligence offerings with a focus on speed and efficiency.

在 Google DeepMind 阅读 →

AI 生成摘要 · Google Gemini · 来自 7 个来源。 我们如何撰写摘要 →

Google DeepMind launches Gemini 3.1 Flash TTS, Live, and Lite models

报道来源 [7]

  1. X — Google DeepMind TIER_1 English(EN) · GoogleDeepMind ·

    RT @GoogleAIStudio: [pumped] gemini 3.1 flash text-to-speech just landed in ai studio.

    RT @GoogleAIStudio: [pumped] gemini 3.1 flash text-to-speech just landed in ai studio. you can now trigger specific vocal delivery like pa…

  2. Google DeepMind TIER_1 English(EN) ·

    Gemini 3.1 Flash TTS: the next generation of expressive AI speech

    Our newest audio model introduces granular audio tags that give you precise control to direct AI speech for expressive audio generation.

  3. Google DeepMind TIER_1 English(EN) ·

    Gemini 3.1 Flash Live: Making audio AI more natural and reliable

    Our latest voice model has improved precision and lower latency to make voice interactions more fluid, natural and precise.

  4. Google DeepMind TIER_1 English(EN) ·

    Gemini 3.1 Flash-Lite: Built for intelligence at scale

    Gemini 3.1 Flash-Lite is our fastest and most cost-efficient Gemini 3 series model yet.

  5. Google DeepMind TIER_1 English(EN) ·

    Gemini 3 Flash: frontier intelligence built for speed

    Gemini 3 Flash offers frontier intelligence built for speed at a fraction of the cost.

  6. Smol AINews TIER_1 English(EN) ·

    Google I/O: new Gemini native voice, Flash, DeepThink, AI Mode (DeepSearch+Mariner+Astra)

    **Google I/O 2024** showcased significant advancements with **Gemini 2.5 Pro** and **Deep Think** reasoning mode from **google-deepmind**, emphasizing AI-driven transformations and developer opportunities. **GeminiApp** aims to become a universal **AI assistant** on the path to *…

  7. TLDR AI TIER_1 English(EN) · TLDR ·

    Gemini 3.1 Flash TTS 🎙️, Agent-to-Person marketplace 🤝, OpenAI Agents SDK 🛠️