Thread

Gemini 3.8 text-to-speech

330 points · 152 comments · swolpers

simonw · 1790183994 · focus · HN ↗
I vibe coded a playground UI for trying this out. The conversation mode is neat, and it's very expensive - most of my experiments have cost less than a cent.
<a href="https://tools.simonwillison.net/gemini-tts-playground#compose=%7B%22v%22%3A1%2C%22mode%22%3A%22single%22%2C%22model%22%3A%22gemini-3.8-flash-tts%22%2C%22single%22%3A%7B%22voice%22%3A%22Kore%22%2C%22style%22%3A%22cheerful%20and%20friendly%22%2C%22text%22%3A%22Have%20a%20wonderful%20day!%22%7D%2C%22speakers%22%3A%5B%7B%22id%22%3A1%2C%22name%22%3A%22Joe%22%2C%22voice%22%3A%22Puck%22%7D%2C%7B%22id%22%3A2%2C%22name%22%3A%22Jane%22%2C%22voice%22%3A%22Kore%22%7D%5D%2C%22turns%22%3A%5B%7B%22speaker%22%3A1%2C%22text%22%3A%22How's%20it%20going%20today%20Jane%3F%22%2C%22style%22%3A%22cheerful%20and%20friendly%22%7D%2C%7B%22speaker%22%3A2%2C%22text%22%3A%22Not%20too%20bad%2C%20how%20about%20you%3F%20Ready%20to%20test%20these%20new%20voices%3F%22%2C%22style%22%3A%22calm%20and%20relaxed%22%7D%5D%7D" rel="nofollow">https://tools.simonwillison.net/gemini-tts-playground#compos...
1. iAMkenough · 1790184165 · focus · HN ↗
  Very expensive?
  1. simonloserson · 1790188105 · focus · HN ↗
    he's vibe writing
2. eis · 1790187207 · focus · HN ↗
  Nice but in general I wouldn't put my API key into some third party website, no matter if it claims to not store it. It's not something personal, you are a bit of a celeb here so I wouldn't think you'd save the keys, it's just good general data hygiene. Especially not if a leaked API key can rack up thousands of dollars in fees quickly.
  1. simonw · 1790188671 · focus · HN ↗
    Sure. Feel free to copy the code and run it yourself instead.
3. mohsen1 · 1790188606 · focus · HN ↗
  Why tho? AI Studio has this model available and I don't need to paste the API key anywhere
  <a href="https://aistudio.google.com/generate-speech?model=gemini-3.8-flash-tts" rel="nofollow">https://aistudio.google.com/generate-speech?model=gemini-3.8...
  1. simonw · 1790188651 · focus · HN ↗
    Because building my own is a better way to understand the capabilities of the model and how to use it - and to verify that it can be used via CORS.
    CyberDildonics · 1790248666 · focus · HN ↗
    Did you 'build' it or did you vibe code it?
    simonw · 1790260688 · focus · HN ↗
    Bit of both. I define "vibe coding" as building without looking at the code at all. For this one I was reading the code to understand how it works, and I then followed up several times to adjust how it was working.
    Full session here: <a href="https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Fa82f3aef2677c623d1776092d6b21224" rel="nofollow">https://tools.simonwillison.net/markdown-svg-renderer?url=ht...
4. simonw · 1790197937 · focus · HN ↗
  Example (topical, pelican themed) audio clip here: <a href="https://simonwillison.net/2026/Sep/23/gemini-tts-playground/" rel="nofollow">https://simonwillison.net/2026/Sep/23/gemini-tts-playground/

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.