Event ·Multi-source

谷歌Lyria 3.5音乐模型登陆Gemini

谷歌在Gemini应用和API中上线Lyria 3.5音乐生成模型。Lyria 3.5可生成包含副歌、桥段等完整歌曲，时长数分钟。模型支持文本提示和最多10张图像输入，输出MP3和WAV格式。所有生成内容均通过Interactions API调度，并嵌入SynthID隐形水印。

Current read

谷歌把Lyria 3.5音乐模型集成到Gemini里，能根据文本和图片生成完整歌曲，还带防篡改水印。

4 sources73° AI heatLast updated 2026/9/4 23:53:05

Evidence

4 sources

Primary sourceIT之家

2026/9/4 23:53:05View source

Related source 1Google Gemini App

2026/9/4 16:22:51View source

Related source 2Decoder

2026/9/6 09:56:24View source

Related source 3Blognone

2026/9/5 09:00:00View source

Conflict check

Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.

Open the story