Business Software for Gemini Live API

Gemini 3.8 Flash-Lite TTS is an expressive text-to-speech model from Google optimized for high-volume, cost-efficient speech generation. It is designed for workloads such as global dubbing, large-scale audio content production, localization, and conversational voice agents. Users can control characteristics such as tone, pacing, emphasis, and expressive nuance to shape how generated speech is delivered. Line-by-line direction allows scripts to include performance instructions and natural speech cues rather than producing uniformly spoken narration. The model supports long-form generation and is designed to preserve voice quality, natural pacing, and character consistency across extended audio. Native two-speaker staging allows developers and creators to generate multi-turn conversations while keeping speakers distinct and maintaining natural turn-taking. Scripted cues can introduce laughs, sighs, gasps, and listening responses such as “mhm” or “yeah” to make dialogue more conversational. Gemini 3.8 Flash-Lite TTS supports more than 100 languages and is designed for multilingual audio experiences at global scale, while generated Gemini Audio output includes SynthID watermarking for transparency. Developers can access the model through Google AI Studio and the Gemini API, with integration into Google Vids and planned API availability through Gemini Enterprise.

Gemini 3.8 Live is a native speech-to-speech AI model from Google DeepMind designed for low-latency conversational agents and real-time voice applications. The model can reason and execute tasks while maintaining the natural flow of an audio conversation. Its asynchronous function calling capability allows external APIs and tools to run in the background without forcing the agent to stop speaking while it waits for results. Developers can combine streamed audio with structured information through incremental content updates, allowing responses to adapt as new data becomes available. Visual context support enables applications to ground conversations in live images or video so agents can understand both what users say and what they are looking at. Gemini 3.8 Live supports more than 97 languages and is designed to maintain consistent accents across multilingual experiences. The model also emphasizes alphanumeric precision for accurately understanding information such as account identifiers, confirmation codes, technical values, and claim numbers. A related Gemini 3.8 Live Extended Thinking model adds configurable reasoning for more complex, multi-step tasks while continuing to interact with the user. Gemini 3.8 Live is available through the Gemini API, Google AI Studio, and integrations with real-time development platforms such as LiveKit, Pipecat, Agora, LangChain, and Vercel.