Suno has added spoken-word generation to its AI music service. The Speech feature is available in public beta on the company’s web and mobile products, where it can create a synthetic voiceover alone or combine that voice with generated background music in a single track.
Simple mode accepts a description such as a character and situation. Advanced mode takes a complete script and adds controls for voice gender, delivery style and the amount of variation between generations. Outputs can run for about eight minutes. Users who want clean narration can disable the music with a toggle.
Generating speech is not new, but Suno is differentiating the feature through its existing music system. That could make it useful for narrated poems, dramatic readings, presentations and other clips that would otherwise require separate voice and soundtrack tools.
Suno describes the release as a genuine beta rather than a finished production tool. The company says accents can drift between regions and dramatic pauses may be exaggerated. Those limitations matter for professional narration, accessibility and any use where a particular accent must remain consistent. The launch also broadens Suno’s product beyond music at a time when its music generator continues to face copyright lawsuits.