Google Introduces Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking Models

Google Introduces Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking Models Google has announced Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, two voice dialogue models designed to offer near real-time reasoning, background tool execution, and enhanced conversational capabilities across developer, enterprise, and consumer products. Gemini 3.8 Live is designed for scale and cost efficiency, while Gemini 3.8 Live Extended Thinking is tailored for high-complexity tasks and multi-step reasoning. Gemini 3.8 Live Extended Thinking scored #1 on Artificial Analysis' Speech to Speech Quality Index (82.6), 68.6% on tau-Voice, 35.1% on Sierra's tau-Voice-banking benchmark, and 97.7% on Big Bench Audio. The models support near real-time visual input processing, mid-conversation switching between 97 languages, and parallel execution of tool and API calls. Generated audio outputs are embedded with imperceptible SynthID watermarks to assist in detecting AI-generated content. Model Features and Benchmark Performance Gemini 3.8 Live Extended Thinking addresses enterprise-level tasks by reasoning and speaking simultaneously, providing natural verbal acknowledgments and progress narration while executing multi-step tasks. In evaluations, it ranked first on the Speech to Speech Quality Index with an 82.6 score, led agentic benchmarks with 68.6% on tau-Voice and 35.1% on tau-Voice-banking, and scored 97.7% on Big Bench Audio. Meanwhile, Gemini 3.8 Live placed second in the Speech Agent Arena, balancing conversational quality with accuracy on ServiceNow's EVA-Bench while supporting visual input processing, 97 languages, and background tool calls. Developer Ecosystem and Watermarking Developer platforms including Agora, Fishjam, LangChain, LiveKit, Pipecat, Vercel, and Vision Agents are integrating the Gemini Live API to manage real-time media streaming infrastructure. External partners such as Salesforce, Genspark, and Lumeris are leveraging the models for their low latency, fluidity, and tool-calling functions. To address content provenance and prevent misinformation, all audio generated by the models incorporates Google's imperceptible SynthID watermark. Availability and Rollout Both models are rolling out through multiple channels. Developers can access both via the Gemini API and Google AI Studio, while enterprises have private preview access through Gemini Enterprise. For general users, Gemini 3.8 Live is available in Search Live. Gemini 3.8 Live Extended Thinking is accessible in Gemini Live, for Google AI Pro and Ultra subscribers in Docs within Workspace, and for Google AI subscribers in Gmail and Keep, with broader enterprise availability coming to Workspace business customers and Gemini Enterprise for Customer Experience.

Google推出Gemini 3.8 Live与3.8 Live Extended Thinking实时语音模型 Google发布了Gemini 3.8 Live和Gemini 3.8 Live Extended Thinking两款实时对话模型，通过近实时推理和并行处理能力，帮助开发者、企业与普通用户通过语音更流畅地处理复杂任务。 Gemini 3.8 Live主打规模化与成本效益，3.8 Live Extended Thinking专攻多步推理等高复杂度任务。 3.8 Live Extended Thinking在Artificial Analysis语音质量指数中位列第一（82.6分），且在多项语音基准测试中处于领先位置。 新模型支持近实时视觉处理、97种语言切换、对话中后台工具调用，且生成的音频均嵌入SynthID水印。 性能表现与交互技术升级 Gemini 3.8 Live Extended Thinking在Artificial Analysis的语音对语音质量指数中获得第一名（82.6分），在τ-Voice和τ-Voice-banking中分别达到68.6%与35.1%的任务完成率，并在Big Bench Audio上斩获97.7%的高分；Gemini 3.8 Live在Speech Agent Arena中获得第二名，且具备高成本效益。功能方面，模型可近实时处理视觉输入，支持在对话中自动识别并切换97种语言。模型能在持续对话的同时在后台执行工具和API调用；Extended Thinking版本还支持边思考边发声，通过语言提示和实时进度讲解呈现多步任务进展。 开发者生态、安全机制与推出时间 开发者可通过Gemini Live API配合Agora、LangChain、LiveKit、Vercel等平台构建语音界面，Salesforce、Genspark和Lumeris也作为合作伙伴接入。所有AI生成的音频均直接嵌入不可见的SynthID水印，确保内容可被检测。两款模型即日起向Gemini API和Google AI Studio开发者开放，并以私有预览形式进入Gemini Enterprise；此外，3.8 Live已接入Search Live，3.8 Live Extended Thinking则面向Gemini Live以及部分Google Workspace和Google AI订阅用户推出。

Sep 15, 2026 | Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking are our most advanced live dialogue models yet. Major upgrades in intelligence and parallel reasoning make them more intuitive to collaborate with and use to execute complex tasks using your voice. Tom Ouyang Principal Engineer Malini Jaganathan Member of Technical Staff, on behalf of the Gemini Audio Team Your browser does not support the audio element. Listen to article [[duration]] minutes This content is generated by Google AI. Generative AI is experimental Updated September 17, 2026 Today, we’re introducing two new models that bring advancements in near real-time reasoning to more effectively enable voice agents and make conversing with AI feel more intuitive and intelligent. Gemini 3.8 Live : Built for scale and cost efficiency, combining conversational intelligence with fluid dialogue and visual grounding. Gemini 3.8 Live Extended Thinking : Built for high-complexity tasks, with increased intelligence and multi-step reasoning. For developers and enterprises, these models deliver the building blocks for reliable, production-ready voice agents. They also make speaking with Gemini across the Gemini app, Google Workspace, and Search more fluid and collaborative — helping you tackle complex tasks using just your voice. Experience more fluid, intelligent conversations Gemini 3.8 Live Extended Thinking provides enterprise-grade task completion and intelligence, capturing the #1 overall spot on Artificial Analysis' Speech to Speech Quality Index (82.6), and leads in agentic task completion with 68.6% on τ -Voice and 35.1% on Sierra’s τ -Voice-banking benchmark. It also provides strong reasoning capabilities, scoring 97.7% on Big Bench Audio, while maintaining a highly competitive price point compared to other frontier models. Gemini 3.8 Live has shown a high preference among users, securing a second place in the Speech Agent Arena . In addition to this performance, it remains highly cost-effective — providing developers and enterprises with a capable and efficient model built for scale. On ServiceNow’s EVA-Bench , a benchmark for evaluating voice agents, our models push the Pareto Frontier for complex workflows by successfully balancing accuracy with conversational quality. Note: This was run on the Live API on Gemini Enterprise Agent Platform. Gemini 3.8 Live processes visual inputs in near real-time, enriching conversations with context for more helpful responses. It automatically detects and transitions between 97 supported languages mid-conversation. It executes tools and API calls in the background while continuing the conversation, so the model can acknowledge requests and keep chatting while tasks finish in the background. For tasks that require deeper reasoning, 3.8 Live Extended Thinking reasons and speaks simultaneously. It delivers increased intelligence for complex workflows while maintaining an uninterrupted conversational flow — using early verbal cues like “Let me check that…” to acknowledge prompts naturally, and live progress narration to walk users through multi-step background tasks as they progress. Across Google Workspace, Search, and the Gemini app, our Live models deliver more intuitive, collaborative experiences — especially when tackling your most complex tasks. Empowering the developer and enterprise voice ecosystem By using the Gemini Live API , developer platforms such as Agora , Fishjam , LangChain , LiveKit , Pipecat , Vercel , and Vision Agents enable developers to build and deploy high-performance voice-driven interfaces with ease. These platforms manage complex real-time media streaming infrastructure behind the scenes, allowing developers to focus entirely on crafting the user experience. We’re also partnering with companies like Salesforce, Genspark, and Lumeris who are excited about 3.8 Live and 3.8 Live Extended Thinking, highlighting its impressive latency, fluidity, and tool-calling capabilities. Ensure transparency with SynthID watermarking All audio generated by our AI products is watermarked with SynthID . This imperceptible watermark is woven directly into the audio output, ensuring AI-generated content remains detectable to help prevent misinformation. For details on our approach to safety and responsibility, review the model card . Start using our latest Gemini Audio models: 3.8 Live is rolling out starting today: For developers : In the Gemini API and Google AI Studio For enterprises : In private preview in Gemini Enterprise and coming soon to Gemini Enterprise for Customer Experience For everyone : In Search Live 3.8 Live Extended Thinking is rolling out starting today: For developers : In the Gemini API and Google AI Studio For enterprises : In private preview in Gemini Enterprise and coming soon to Gemini Enterprise for Customer Experience and Google Workspace business customers For everyone : In Gemini Live and for Google AI Pro and Ultra subscribers in Workspace in Docs, and all Google AI subscribers in Gmail and Keep Get the latest news from Google in your inbox Sign up for our newsletters with product updates, event information, special offers, and more. Your information will be used in accordance with Google's privacy policy. You may opt out at any time.