Gemini 3.8 TTS Playground

Google 今日发布了两款新的 Gemini 文本转语音模型：gemini-3.8-flash-tts 和 gemini-3.8-flash-lite-tts。

它们提供了超过 2,000 种声音的语音库，并支持仅使用“一段 30 秒的、属于你本人声音或你拥有使用权的声音音频样本”创建自定义声音。

我借助 GPT-6 Astra，以 vibe coding 的方式开发了这个自带 API Key 的 Playground 界面，并利用了底层 Gemini API 开放的 CORS 策略。

该 API 的一个值得注意的特性是：它可以轻松定义由多个角色参与的完整对话，并为每个角色分别指定不同的声音和语音风格指令。

下面是一段简短的音频演示：两只鹈鹕正在讨论是否应搬去Pacifica Pier。我让 Claude 4.5 Opus 编写脚本，并生成了一个使用该工具渲染脚本的 URL。

您的浏览器不支持 audio 元素。

使用 Gemini 3.8 Flash TTS（而非价格更低的 Flash-Lite）生成 1 分 18 秒音频大约需要 20 秒，成本为 2.74 美分。

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.