Google DeepMind's Lyria 3.5 Launches on fal

fal has added Google DeepMind's Lyria 3.5 text-to-music model to its platform, letting users generate songs from written prompts.

Google DeepMind's music generation model Lyria 3.5 is now accessible through fal, according to an announcement on X from the platform's official account. The integration gives fal users a new way to turn written prompts directly into finished musical output. According to fal, Lyria 3.5 can take detailed text prompts and translate them into music that blends multiple genres and instrumental styles within a single track. The model is also described as able to shape vocal delivery and control musical dynamics purely through text instructions, rather than requiring users to manually adjust audio parameters. The move adds another generative audio option to fal's lineup of AI model integrations, positioning text-to-music generation alongside the video and image tools the platform already hosts. For creators working across AI video and multimedia projects, having a text-driven music model available on the same platform could streamline workflows that previously required sourcing audio elsewhere. Beyond the details shared in fal's post, no further specifics have been released about pricing, output length, or how Lyria 3.5 compares to earlier versions of Google DeepMind's music models. As with many new model integrations, more detail is likely to emerge as users begin testing its capabilities firsthand.