Suno's AI Now Makes Voiceovers with Music

Suno, a company that uses AI to make music, just launched a new feature called Speech. It lets you create spoken audio with background music. You can type what you want it to say, or describe the kind of voice you want, like 'a pirate captain rallying his crew.' Then Suno generates a track with both voice and music. It's available now in public beta on Suno's website and mobile apps. This is a big deal because it means anyone can produce professional-sounding voiceovers without hiring actors or renting a studio.

So why should you care? If you make videos, podcasts, or presentations, this could save you a lot of time and money. Instead of recording yourself or paying for voice talent, you can just type and get a voiceover with matching music. It's like having a personal audio producer in your pocket. The feature has two modes: Simple, where you describe what you want, and Advanced, where you provide a script and adjust voice gender, style, and variety. The maximum length is about eight minutes.

But there's a catch. Suno admits the feature isn't perfect yet. They say 'beta really does mean beta.' For example, British accents might wander to Australian, and dramatic pauses can be overly dramatic. Also, AI-generated speech is not new—companies like ElevenLabs and Adobe already offer similar tools. Suno's twist is combining voice and music seamlessly. This move also helps Suno diversify, as its music generator has faced lawsuits from record labels.

Overall, this is another step toward making advanced audio production accessible to everyone. Whether you're a content creator, a teacher, or just someone who wants to make a fun audio greeting, Suno's Speech could be a handy tool. Just don't expect perfection yet.