Suno adds AI-generated spoken-word feature with optional background music

Suno expanded its AI music platform by launching a Speech feature in public beta across its web and mobile apps. Users can generate synthetic voiceovers either by describing the desired content or by providing a full script, with options to adjust voice gender, speech style, and variation. The tool automatically blends the spoken track with AI-produced background music, though a toggle allows the music to be removed for clean speech.

Each generated piece can be up to roughly eight minutes long. Suno acknowledges the beta’s imperfections, such as occasional accent shifts, and says future updates will be driven by user feedback. The move aims to diversify Suno’s offerings beyond music generation.