# fofr 实测 Lyria 3.5 音乐生成模型并分享音频输出示例

- 来源：fofr (@fofrAI)
- 发布时间：2026-09-05 00:54
- AIHOT 分数：54
- AIHOT 链接：https://aihot.virxact.com/items/cmtn7mi340pkgromyttbrwrji
- 原文链接：https://x.com/fofrAI/status/2095918540989583660

## AI 摘要

Google 在 AI Studio、Gemini API 和 Gemini app 中推出音质最佳的 Lyria 3.5 音乐生成模型，带来更具表现力的人声和更丰富的编曲。作者分享了自己的实测音频，提示词为多人在俱乐部交谈、无实际演唱，认为人群嘈杂声真实又难以辨别，是其最喜爱的输出之一。

## 正文

I've been experimenting with Lyria 3.5, and this is one of my favourite ever audio outputs. I love how real but indiscernible the chatter of the crowd is.

Prompt: "just a conversation between many people in a club, no actual singing"

I can't help but feel like I'm missing out.

### 引用推文

> Google AI Studio：Lyria 3.5, our best-sounding music generation model, is now available in AI Studio, via the Gemini API, and in the Gemini app this model brings more expressive ...