Suno adds Speech feature to generate voice and background music

In short: Suno, best known for making AI music, has launched a public beta feature that can generate spoken voiceovers, with optional background music.

What happened

Suno announced a new feature called Speech. It is now available as a public beta, meaning anyone can try it while Suno continues to test and improve it. Speech works on Suno’s website and its mobile apps.

With Speech, you can type a script or describe what you want, and Suno will generate a synthetic voice (a computer-made voice that reads the words out loud). Suno also lets you generate background music at the same time, so the result is one combined audio track. If you only want the voice, you can turn the music off with a toggle.

Suno says the goal is to make spoken audio that fits different situations, like poems with calm music or more energetic voiceovers for dramatic readings. In the product, users can find it by going to the “Create” tab and then choosing the Speech option.

Suno is not the first company to offer AI voices. Other tools already do text-to-speech, which is software that reads text out loud like an automated narrator. The Verge notes that Suno’s twist is pairing generated speech with music in the same workflow.

Why it matters

More people and small teams now have an easy way to make narrated audio for videos, podcasts, and social posts, even if they do not have a microphone setup or a music library. At the same time, AI voice tools raise familiar questions about how voices are used and who has permission, so it is worth paying attention to how Suno handles safety and rights as the beta expands.

Source: The Verge AI