Suno Can Now Turn Your Writing Into Spoken Audio

Suno has launched Speech, a new test feature that reads your writing out loud in an artificial voice. It is available in public beta on Suno's website and mobile apps. The Verge

You find it under Create, then Speech. There are two options. Simple mode lets you describe what you want to hear. Advanced mode lets you paste in your full script to be read word for word.

Advanced settings let you pick the voice gender, speaking style, and how much vocal variety you want. Audio can run up to about eight minutes. That is long enough for a podcast section, a how-to explainer, or short narration.

Speech can create the voice and the background music together as one track, like recording a narrator and background piano at the same time. A switch turns the music off for voice only. Chief product officer Jack Brody called it "the first audio model that generates voice and music together as one cohesive track." Suno said it will keep improving Speech based on user feedback and said the test version is imperfect.

Suno introduced Speech in beta on October 1, 2026, in its official post titled "Introducing Speech (beta)." Suno The company already has a separate Voices feature that lets people add their own voice to Suno-made songs. That system compares a person's speech to an uploaded voice recording and is closed to users under 18.

The broader context here is a change in how Suno builds its technology. Suno replaced its AI models with a new model trained on licensed music. TechCrunch It rolled out AI models trained in cooperation with major music industry players. The company bought WavTool for its AI music editing tools, a web editor that launched in 2023. Suno raised more than $400 million at a $5.4 billion valuation. Reuters

In my view, the voice-plus-music combination is what to watch. Most tools today make the voice and the music separately, then mix them later. Making them together saves time for people working alone. It can also make the voice harder to hear or the music a poor fit. The music switch and voice controls help. The real test will be steady quality across tries, correct pronunciation in long scripts, and clean voice sound when music is on. If Suno fixes those issues during testing, Speech could become a quick way to draft narrated pieces without picking music by hand.