<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>Music on Christian Roy</title>
    <link>https://christianroy.dev/tags/music/</link>
    <description>Recent content in Music on Christian Roy</description>
    <generator>Hugo -- 0.156.0</generator>
    <language>en-us</language>
    <lastBuildDate>Sun, 31 May 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://christianroy.dev/tags/music/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>NOVA·FM: an endless AI radio station built on Stable Audio 3</title>
      <link>https://christianroy.dev/til/novafm-endless-ai-radio-station-stable-audio-3/</link>
      <pubDate>Sun, 31 May 2026 00:00:00 +0000</pubDate>
      <guid>https://christianroy.dev/til/novafm-endless-ai-radio-station-stable-audio-3/</guid>
      <description>&lt;p&gt;NOVA·FM is a radio station with no library and no playlist. Every
track is composed on the spot, seconds before it reaches your ears,
then fades and is never reheard in quite the same shape. I built it
in two days with Claude Code (Opus 4.7 and 4.8), guided by me, on
top of Stable Audio 3, Stability AI&amp;rsquo;s open-weight audio model family
released earlier this month.&lt;/p&gt;
&lt;p&gt;More than seven stations so far, each a mood rather than a folder:
lo-fi, synthwave, cinematic, deep house, jazz, ambient, classical,
and a few more I keep adding. Two ways to listen: a private dial
that&amp;rsquo;s just for you, and a shared live signal where everyone tuned
in hears the same track at the same second.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Google DeepMind&#39;s Lyria 3 generates full songs from a photo or a sentence</title>
      <link>https://christianroy.dev/til/lyria3-music-gen/</link>
      <pubDate>Wed, 18 Feb 2026 00:00:00 +0000</pubDate>
      <guid>https://christianroy.dev/til/lyria3-music-gen/</guid>
      <description>&lt;p&gt;Lyria 3 takes a text prompt or an image and produces a complete track: instrumentation,
vocals, lyrics. Not a loop, not a mood board. A song.&lt;/p&gt;
&lt;p&gt;The image input is what makes it interesting. Most generative audio models take text.
Lyria 3 can look at a picture and decide what it sounds like. That&amp;rsquo;s a different kind
of creative interpretation, closer to how a composer might respond to visual art than
to a spec.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
