google-gemini/gemini-live-api-examples

View on GitHub

Gemini Live provides multimodal realtime agent capabilities. Build voice agents that can process vision and text in realtime.

Stars: 496
Forks: 175
Open beginner issues: 0
Indexed issues: 8
Avg merge: 6m
Merged PRs (30d): 1

Dominant language: JavaScript
License: No license data
Last GitHub push: Sep 15, 2026
Latest indexed: Sep 16, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed

Open All

8 open issues indexed

GEMINI LIVE API LOOSING TEXT ON LONG CONVERSATION Open

google-gemini/gemini-live-api-examples#26 · 1 comment · 1 reaction · 0 assignees · Indexed Sep 16, 2026
Integration proposal: Virtuosis voice biomarkers for Gemini Live Open

google-gemini/gemini-live-api-examples#35 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
`gemini-3.1-flash-live-preview`: a 1.0 s mid-sentence pause closes the turn while the caller is still speaking (+ empty generation when `thinking_level` is set) Open

google-gemini/gemini-live-api-examples#37 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
`gemini-3.1-flash-live-preview`: a turn left open after an ignored utterance never closes on its own; the caller's next sentence is consumed to close it with zero output tokens Open

google-gemini/gemini-live-api-examples#38 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 16, 2026
Reconnect penalty Open

google-gemini/gemini-live-api-examples#39 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
gemini-live-2.5-flash-native-audio on Vertex: the model streams full-length audio at near-zero amplitude — the caller hears silence while every metric looks healthy (5.9% of production calls) Open

google-gemini/gemini-live-api-examples#40 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
input_audio_transcription returns fabricated content in unspoken languages while the model understands the audio correctly (Arabic, gemini-3.1-flash-live-preview) Open

google-gemini/gemini-live-api-examples#45 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
`gemini-3.1-flash-live-preview`: the model repeats the same sentence 2–4 times inside one generation (~7 s of silence between each) before releasing the toolCall Open

google-gemini/gemini-live-api-examples#46 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026

google-gemini/gemini-live-api-examples

Get new issues in your inbox