Suno Speech: voice and music generated as one track
A new Suno beta reads your text over original music. The company calls it the first model to generate voice and music together.
On October 1, Suno opened its Speech beta to all users. It generates spoken audio over original music, and the company claims it’s the first audio model to create voice and music together as one cohesive track.
What’s new
Speech is built into Suno. You enter an idea, a poem or your own writing, then describe the voice and musical style you want. Suno’s examples include:
- dramatic readings of texts from friends;
- voice notes with epic scores;
- meditations, poems and pep talks;
- bedtime stories.
How to try it
Suno tested the feature with a small group for about a month before opening the beta. It’s now available to all users inside the product.
Limitations
Suno itself flags two issues: accents can drift, for example from British to Australian, and dramatic pauses can come out exaggerated. The announcement doesn’t cover pricing, limits, output length or supported languages.
Prepared with AI from public sources.