Gemini 3.8 TTS Playground

Google released two new Gemini text-to-speech models, gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, which ship with a library of over 2,000 voices and can create a custom voice from a 30-second audio sample. Developer Simon Willison built a bring-your-own-key Gemini 3.8 TTS Playground interface using GPT-6 Astra, and reported that generating 1 minute 18 seconds of multi-character audio with Gemini 3.8 Flash TTS took about 20 seconds at a cost of 2.74 cents.

Tool: Gemini 3.8 TTS Playground https://tools.simonwillison.net/gemini-tts-playground Google released two new Gemini text-to-speech models https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-text-to-speech/ today - gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts . They come with a library of over 2,000 voices, plus the ability to create a custom voice with "just a 30-second audio sample of your voice or a voice you have the rights to use". I vibe coded https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Fa82f3aef2677c623d1776092d6b21224 this bring-your-own-key playground interface with GPT-6 Astra, taking advantage of the open CORS policy of the underlying Gemini API. A notable feature of the API is that it makes it easy to define a full conversation between multiple characters, each with different voices and voice style instructions. Here's a short demo clip of a conversation between two pelicans debating if they should move to the Pacifica Pier https://simonwillison.net/2026/Sep/12/sighting-399708714/ . I had Claude 4.5 Opus write the script https://claude.ai/share/3597fc77-9323-4583-aeb9-b0e4c3f654a3 and generate a URL to render it using the tool https://simonwillison.net/u/vj . It took ~20 seconds to generate 1m 18s of audio using Gemini 3.8 Flash TTS not the cheaper Flash-Lite , at a cost of 2.74 cents. Tags: text-to-speech https://simonwillison.net/tags/text-to-speech , gemini https://simonwillison.net/tags/gemini