Simon Willison vibe-codes a Gemini 3.8 TTS playground: 1m18s audio for 2.74¢
Simon Willison · rss · 2026-09-24
Google released two new text-to-speech models, gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, with 2,000+ preset voices and custom voice cloning from a 30-second sample. Simon Willison vibe-coded a bring-your-own-key playground with GPT-6 Astra, leveraging the Gemini API's open CORS policy. A standout API feature is easy multi-character conversations with distinct voices and style instructions — demoed with a two-pelican debate scripted by Claude 4.5 Opus. Generating 1m18s of audio took 20 seconds and cost 2.74 cents with Flash TTS.
More from coding & agent
- Why AI-made dev tools beat one-shot game generation: freedom of process — eschadiol · 2026-09-24
- RealSense VP on AgenticROS: Letting AI Agents Directly Control Physical Robots — chrismatthieu · 2026-09-24
- AWS API Gateway's Hard 10MB Upload Limit and the Presigned URL Fix — _jaydeepkarale · 2026-09-24
- Open-source Pragma gives coding agents a terminal-first workspace with Git worktrees — tech_w0rld · 2026-09-24
- Dev builds dense task annotation system with GPT-6 Astra, ships it as an LLM skill — chris_j_paxton · 2026-09-24
- Jev-as-a-Judge: hybrid agent eval flow escalates low-confidence calls to frontier models — omarsar0 · 2026-09-24