Simon Willison Builds a Bring-Your-Own-Key Voice Playground with Gemini 3.8 TTS
Google released two text-to-speech models, gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, offering more than 2000 voices and support for creating custom voices from 30-second audio samples. Leveraging the Gemini API's open CORS policy, Simon Willison quickly built a bring-your-own-key Playground with GPT-6 Astra and demonstrated speech generation for multi-character dialogue. In his test, generating 1 minute 18 seconds of audio with Gemini 3.8 Flash TTS took about 20 seconds and cost 2.74 cents.
Why read this
AI score 59
The author tested Gemini 3.8 TTS with a self-built playground, sharing reusable details such as 2000+ voices, 30-second cloning, and generation costs.
Topics
Body
23rd September 2026
Google released two new Gemini text-to-speech models 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 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 . I had Claude 4.5 Opus write the script and generate a URL to render it using the tool .
Your browser does not support the audio element.
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.
This is a beat by Simon Willison, posted on 23rd September 2026 .
Pay me to send you less!