livekit-plugins-google

What it is and what it does

This package is a plugin for LiveKit Agents that bridges Google Cloud AI services into real-time conversational applications. It provides integrations for Gemini and Gemini Live models, Cloud Speech-to-Text for transcription, and Cloud Text-to-Speech for audio synthesis. The plugin abstracts away the complexity of wiring these services together, letting you build voice-based agents that can listen, understand, reason, and speak using Google's AI models.

You'll need a Google Cloud account with credentials configured (either passed directly or via Application Default Credentials) and the respective APIs enabled for your project. The package supports multiple Gemini Live models across both the Gemini Developer API and Vertex AI, though they have different model names and slightly different behavior. It's designed for developers building real-time interactive applications like voice assistants or conversational bots.

Use it for:

• Build real-time voice assistants using Gemini Live API with native audio streaming.
• Add speech-to-text transcription to LiveKit video/voice applications via Cloud Speech-to-Text.
• Synthesize natural-sounding responses with Cloud Text-to-Speech in agent conversations.
• Create interactive conversational agents that understand and respond in real time.
• Deploy multi-modal AI agents combining video, audio, and text in LiveKit sessions.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Integrates Google Cloud AI services (Gemini, Speech-to-Text, Text-to-Speech) with LiveKit Agents for building real-time conversational applications.

Yes, if you're building real-time conversational applications with LiveKit and want to use Google's AI services. The package is actively maintained, has low install friction, and integrates cleanly with the LiveKit Agents framework. Requires a Google Cloud account and API setup; not suitable if you need offline-only or non-Google AI backends.

Install

livekit-plugins-google on PyPI

pip install livekit-plugins-google

uv add livekit-plugins-google

poetry add livekit-plugins-google

Installing livekit-plugins-google

Before you install

Low friction install with a pure-Python wheel. The package is actively maintained with a recent release and depends on well-established Google Cloud libraries, though you'll need Google Cloud credentials and enabled APIs.

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions; suitable for most projects.

Quickstart

pip install livekit-plugins-google

from livekit.agents import google

# Use with LiveKit agents framework
# Requires google-auth credentials and enabled Google Cloud APIs

Requires Python 3.10 or later, a Google Cloud account with credentials, and enabled Cloud Speech-to-Text and Cloud Text-to-Speech APIs.

Verify before relying

• Whether Gemini Live API models (gemini-3.1-flash-live-preview, gemini-2.5-flash-native-audio-preview variants) are production-ready or still in preview.
• Pricing and quota implications of using multiple Google Cloud services (Speech-to-Text, Text-to-Speech, Gemini) simultaneously.
• Whether the package handles automatic credential refresh or requires manual management.

Package facts

Evidence: livekit_plugins_google-1.6.10-py3-none-any.whl

Keywords: ai, audio, gemini, google, livekit, realtime, video, voice

Tags

More Artificial Intelligence packages

Further reading