# google-gemini/live-api-web-console

A react-based starter app for using the Live API over websockets with Gemini

Repository: https://github.com/google-gemini/live-api-web-console
Canonical: https://ross.abutalabs.com/products/live-api-web-console
Homepage: https://ai.google.dev/api/live
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: gemini, gemini-api
Last push: 2026-06-21T04:26:51+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 88, release rhythm 35, longevity 45
- inputs: {"age_days": 632, "days_push": 73, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2558, forks 734 (observed 2026-08-28T04:07:00.881873+00:00)

## What it is
A React-based starter application for building real-time multimodal experiences with Google's Gemini Live API over WebSockets. It provides modules for streaming audio playback, microphone/webcam/screen capture, and a unified log view to aid development.

## Use cases
- build a voice assistant with gemini live api
- stream audio and video to gemini over websockets
- prototype a real-time multimodal chat app
- test gemini live api function calling and google search grounding
- capture microphone and screen input for an ai assistant
- debug live api websocket sessions with a log view

## When to choose
- you want a ready-made React starting point for the Gemini Live API
- you need streaming audio/video input and playback wired up quickly
- you want example demos of tool use, grounding, and proactive audio

## When to avoid
- you need a production backend rather than a client-side starter app
- you use a different LLM provider than Gemini
- you want a non-React stack

## Facets
- artifact type: application
- maturity: active
- function: websocket, audio-processing, speech-recognition, chatbot, agent-framework, developer-tools
- domain: artificial-intelligence, large-language-models, chatbots, web-development, developer-tools
- platform: cross-platform
- tags: gemini-api, live-api, multimodal, starter-app, react, voice-assistant, websocket-streaming, google-ai, web-server, nodejs

## Member repositories
- google-gemini/live-api-web-console (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:00.881873+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:23:38.117879+00:00, confidence not recorded.
  - readme: https://github.com/google-gemini/live-api-web-console (fetched 2026-08-28T04:07:00.881873+00:00, sha b64e3082c60c)
  - homepage: https://ai.google.dev/api/live (fetched 2026-08-29T10:06:26.430010+00:00, sha cb1aa8b89633)
  - site_page: https://ai.google.dev/gemini-api/docs (fetched 2026-08-29T10:06:26.433282+00:00, sha 11489b3a3b69)
  - site_page: https://ai.google.dev/gemini-api/docs/api-versions (fetched 2026-08-29T10:06:26.435241+00:00, sha f74466e64ddf)
- Data as of 2026-08-30T08:39:29.467469+00:00.