Suno built its name on songs. Now it wants to generate the spoken word too. On October 1 the company opened Speech (beta) to all users on mobile and web, describing it as the first model to create a voice and its background score in one pass.
The workflow is prompt-driven. A user types a poem, a story or an idea, then describes the voice and the musical style. Out comes narration set to original music. Chief Product Officer Jack Brody, in a company blog post, offered examples such as bedtime stories over soft piano and hype speeches over stadium drums.
Suno said it tested the model internally for a month, turning friends’ texts into dramatic readings and giving voice notes cinematic scores. It is careful to call the launch a beta. A British accent can drift into Australian, it warns, and dramatic pauses may be very dramatic.
Speech caps a busy stretch. Suno launched its v6 music-generation family on September 9 with partners Warner Music Group, BMG and Believe, and shipped Studio 2.0 in August.
The company frames the larger opportunity as creative entertainment, a category it argues will define the next wave of consumer technology. Speech bets that the engine behind a chorus can also tell a story, and that users will pay for both.
