{"data":{"id":"7a89cf2a-d2a0-4e58-bb1e-3618102574ac","title":"Gemini Live audio","summary":"Google released Gemini 3.8 Live and 3.8 Live Extended Thinking, two new speech-to-speech models (AI systems that convert spoken words into responses) similar to OpenAI's GPT-Live family. A web UI was created that lets users select a model and voice, enter an optional system prompt (instructions given to the AI before interaction), and have voice conversations through a browser, including the ability to interrupt the model while speaking. The implementation connects to Google's WebSocket endpoint (a two-way communication channel between a browser and server) and uses Web Audio API (a tool for capturing and playing back sound in browsers) for audio capture and playback.","solution":"N/A -- no mitigation discussed in source.","labels":["industry"],"sourceUrl":"https://simonwillison.net/2026/Sep/15/gemini-live/","publishedAt":"2026-09-15T22:47:07.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedVendors":["Google"],"affectedVendorsRaw":["Google","Gemini","OpenAI","GPT-Live","GPT-6 Astra Extra High"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-09-15T22:47:07.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":"api","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}