Google ships Gemini 3.8 Live speech-to-speech models; Willison builds a zero-dependency web UI
Simon Willison · rss · 2026-09-16
Google released Gemini 3.8 Live and 3.8 Live Extended Thinking, two speech-to-speech models similar in shape to OpenAI's GPT-Live models.
Simon Willison had GPT-6 Astra Extra High read the docs and build him a web UI for trying the new models:
- Pick a model and voice preset, set an optional system prompt, and start a voice conversation in the browser
- Supports interrupting the model mid-speech
- Zero dependencies: connects directly to the Gemini BidiGenerateContent WebSocket endpoint and uses a single Web Audio API AudioContext for both capture and playback
A handy minimal reference for wiring up Gemini's realtime voice API.
More from Models
- Open-source VoxLock tops Krisp voice isolation benchmark with 4.95% WER — Arbaz Siddiqui · 2026-11-02
- Anthropic's 85% inference margin sparks debate on open source's price-pressuring role — code_star · 2026-11-02
- User reports xAI appears to have quietly raised weekly usage limits, dropping his meter from 93% to 47% — XFreeze · 2026-11-02
- Meituan's LongCat-2.5 lands as 1.6T MoE agent model, with DeepSeek copycat speculation — teortaxesTex · 2026-11-02
- Asked what AI firms want you to stop owning, Claude said: your own compute — alex_verem · 2026-11-02
- Is Hermes Still Worth It? Codex's $200 Tier Now Overlaps Most of Its Value — Foreign_Lead_3582 · 2026-11-02