Suno Opens Speech Beta to Generate Spoken Words and Music in One Track
The tool brings poems, meditations and dramatic readings into Suno’s creative lineup. The company warns that accents can drift and pauses can become exaggerated.
Loading page…
The tool brings poems, meditations and dramatic readings into Suno’s creative lineup. The company warns that accents can drift and pauses can become exaggerated.
Listen to this story
Suno’s Speech beta adds a text-to-audio format for spoken-word pieces, with users choosing a voice and musical style to accompany their writing. The feature extends Suno beyond song generation, but its performance control is still imperfect: the company says accents can shift and dramatic pauses can become exaggerated. For users, that means Speech offers a new way to make meditations, stories, and other spoken creations, but not yet a guarantee of precise delivery.
The public beta followed a month of testing with a small group.
Suno’s examples include overproduced readings of friends’ texts, epic-scored voice notes, meditations, pep talks, and children’s bedtime stories.
CEO Mikey Shulman told Bloomberg that Suno aims to become a destination for creative entertainment beyond music.
Suno is giving written words a different route into audio: a spoken performance with its own musical backing, rather than a song. On October 1, the company opened the public beta of Speech, which it says generates voice and music together as one cohesive track.
The release broadens what people can make inside Suno without changing the company’s stated commitment to music. The emphasis is personal expression, including creations that may matter mainly to the person making them.
Suno’s existing service centers on generating songs across genres, complete with lyrics. Speech complements that offering with spoken-word creations, Bloomberg reported.
The described starting point is text: an idea, a poem or something the user has written. Users then describe the voice and musical style they want.
Speech is built directly into Suno. They are company examples, not independent assessments of the results.
The opening follows a month of testing with a small group, according to Suno. Wider access does not mean the company considers Speech finished. It warns that British accents can drift toward Australian ones and back, and that dramatic pauses can become exaggerated. Those are concrete limits on how faithfully the output may follow a requested performance.
The company says it will keep improving Speech based on what people enjoy, what fails and what they want next.
Chief executive Mikey Shulman discussed Speech at Bloomberg’s Screentime conference in Los Angeles on October 1. He said Suno wants to become a destination for creative entertainment beyond music, according to Bloomberg News coverage carried by NDTV Profit.
Loading discussion...
Join the conversation
Explain when a surprising performance would delight you or spoil the result.
Be the first to share a perspective or an experience.
Reader comments
Newest comments first. Replies stay oldest first.