Suno Speech: how to generate voiceovers with AI music

According to The Verge, Suno expanded beyond AI-generated music by launching a new Speech feature in public beta for web and mobile platforms. The tool generates spoken voices from scripts or prompt descriptions, allowing users to create voiceovers accompanied by background music.

How does Suno Speech work for creators?

The feature offers two main modes to handle different production needs. The Simple mode lets users describe the desired audio through a prompt box, while the Advanced mode accepts custom scripts for precise text delivery.

Advanced settings also provide manual control over the AI voice's gender, speech style, and variation levels. Each generated track supports a maximum duration of around eight minutes, making it suitable for short narration tasks and podcasts.

Can you remove the background music?

Yes, the music generation is entirely optional. Users can turn off the background track using a simple toggle if they only need clean synthetic speech for their projects.

Jack Brody, Suno's chief product officer, stated that the model generates voice and music together as a cohesive track. However, the company warns that the beta version still exhibits quirks, such as unpredictable accent shifts and exaggerated pauses.