AI music platform Suno announces speech generation feature

Suno, known in the field of artificial intelligence music, has launched its new feature capable of generating speech sounds based on text or prompts in a public beta version.

Voice and Music Integration

Suno has taken a new step beyond artificial intelligence music production, enabling users to create speech audio from scripts and prompts.

Thanks to this innovative feature, users gain the ability to produce background music and voiceovers simultaneously and as a cohesive track.

Feature Details and Modes

This new tool, made available on Suno's web and mobile platforms, comes with two separate modes offering different use cases for content creators.

While the Simple mode allows for quickly describing content with a prompt box, the Advanced mode permits adjusting gender, style, and variety using a custom script.

Duration Limit and Future Plans

The company noted among the details that the maximum duration of speech content generated by artificial intelligence is around eight minutes.

It is stated that this feature, currently in the beta phase, will continue to be constantly developed in line with user feedback.