AI music maker Suno can now generate voiceovers
What's the story
Suno, a leading player in the AI music space, has launched a new feature that creates spoken voices from scripts or prompted descriptions. The innovative tool is now available in public beta on both web and mobile platforms. It allows users to generate voiceovers and their accompanying background music simultaneously.
Feature overview
'Music will always be at the heart of Suno'
Suno's Chief Product Officer Jack Brody announced the new feature saying, "Music will always be at the heart of Suno and what we build."
He added that their vision has always extended to other forms of human expression.
The new tool, dubbed Speech, is the first audio model that generates voice and music together as one cohesive track.
Unique approach
Unique take on text-to-speech tools
Suno's Speech feature is a unique take on text-to-speech tools, combining AI music with generated voices.
The user can easily turn off the background music with a toggle if they just want clean speech.
This innovative approach could be particularly useful for generative spoken word applications like calming soundtracks for poems or energetic ones for dramatic voiceovers and encouraging speeches.
User guide
How to use speech feature on Suno?
To use the Speech feature, users have to select the "Create" tab and navigate to the Speech option.
There are two modes: Simple and Advanced. The Simple mode lets you describe what you want to create via a prompt box, while the Advanced mode allows adding a custom script if you already know exactly what you want it to say.
Customization options
Limitations of the speech feature
The Advanced mode also lets you customize the gender of the AI voice, speech style, and how much variety each voice generation will have.
However, it's worth noting that the Speech feature has a maximum duration of around eight minutes.
Despite these limitations, Suno assured users that they'll continue to improve Speech based on user feedback.