AI product
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.
3 uses taken from transcripts — each links to the moment in the video.
A live audio-to-audio API for building voice agents that listen and respond in real time, support interruption, stream audio, and call application tools.
Low-latency real-time voice and vision API — a stateful WebSocket session taking text, audio and video and streaming back audio plus transcript
Documentation for the Gemini Live API, a low-latency stateful WebSocket API for building real-time multimodal voice and vision agents. You send text, audio and video frames in and stream back audio chunks plus transcripts, with barge-in interruption, tool calls, Google Search grounding and 90 supported languages.
2 in the library.