Gemini 3.5 Live Translate

Gemini Live API is a Google API for building low-latency, real-time voice and vision applications with Gemini. It uses a stateful WebSocket connection to accept continuous audio, image, and text streams and return spoken audio, transcripts, and other model responses. The API supports barge-in interruption, function calling, Google Search, proactive audio, affective dialog, live transcription, and live voice-to-voice translation. Inputs can include raw 16-bit PCM audio, JPEG images, and text; audio responses are streamed as raw 16-bit PCM audio. Applications can connect server-to-server or directly from a client using WebSockets, with ephemeral tokens recommended for production client connections.

Google's developer API for building applications with Gemini large language models. It provides access to models like Gemini 2.0 Flash and 2.5 Pro, and also supports Gemma open models. Developers use it for tasks such as custom model testing, retrieval, memory, and tool-calling systems.

Gemini TTS is an AI text-to-speech service accessed through the Gemini Interactions API. It generates spoken audio from text using the API's audio response modality.

Gemma Translator is an open-source, on-device voice-translation application designed to run on a Raspberry Pi 5 with 8GB RAM. It runs the Gemma 4 e2b model locally through LiteRT-LM and uses Moonshine for speech recognition and text-to-speech, providing a two-lane interface for conversations between two people. Each lane records speech, transcribes it, translates it with Gemma, and speaks the result in the other lane’s selected language. The React/Vite frontend communicates with a Python API server and is styled for small displays such as 480×320 kiosk screens. The repository includes model-download, startup, and deployment scripts, production Raspberry Pi OS systemd kiosk service registration, Chromium autostart, and support for development or production modes and landscape active-person or vertical two-operator keyboard layouts. After setup and model download, inference runs without an internet connection.