The Speech feature from the company Suno accepts a description of the voice and musical style
In the Speech feature, you can describe the desired voice and musical style and create spoken word with music in a single track. According to the company Suno, the public beta was preceded by a month of testing with a small group. The feature is available on the website as well as in the mobile apps.
Newer information about the Speech feature clarifies that the user enters an idea or custom text along with a description of the desired voice and musical style. The feature creates the spoken word and musical backing together in a single audio track. According to the company Suno's chief product officer, the launch was preceded by a month of testing with a small group of users.
The company Suno has made the Speech feature available in public beta on the website and in the mobile apps. Simple mode works with a description of the desired recording, while Advanced mode allows inserting a custom script and adjusting the voice's gender, delivery style, and the degree of generation variability. The musical backing can be turned off, and the maximum recording length is approximately eight minutes.
According to the company Suno, the feature can be used for example for poems, meditations, and bedtime stories. At the same time, the company acknowledges beta shortcomings: a requested British accent may sound Australian, and dramatic pauses may be disproportionately long. The company has not disclosed how the model was trained.
Why it matters
Creators of spoken recordings can prepare voice and musical accompaniment in one step, or create speech alone. A custom script allows specifying the exact wording, but the approximately eight-minute limit restricts the length of the output. Before using the recording, it is necessary to check the accent and the pauses, for which the company acknowledges errors.
Release card
Speech
Suno
- Inputs
- The input is a text description or a custom script along with a description of the voice and musical style. The output is an audio track with spoken word and optional musical backing.
- Availability
- The model is available in public beta through the Speech feature on the website and in the mobile apps of the company Suno.
- Creating spoken poems with musical backing.
- Creating meditations.
- Creating bedtime stories.
- The requested British accent may sound Australian.
- Dramatic pauses may be disproportionately long.
- The length of a single recording is limited to approximately eight minutes.
The article compares the model with text-to-speech tools and cites the joint generation of voice and musical backing in a single track as its distinguishing feature.
The card summarizes information from the article and any dated corrections, with a link to the original source. It is not our assessment of the model. It does not yet have a dedicated editorial profile. Model selection and other announcements →
What was added since the original report
Verified updates
-
Before launch, Suno tested Speech for one month with a small group of users.; The user can enter a description of the desired voice and musical style.
- Before launch, Suno tested Speech for one month with a small group of users.
- The user can enter a description of the desired voice and musical style.
Two audiences, two different impacts
What this means
For individuals
An individual can convert their own text into a spoken recording and choose the delivery and optional musical accompaniment, for example for a poem or a bedtime story.
For a business
When preparing short commentary recordings, voice and musical backing can be obtained together in a single track. However, checking the delivery remains part of the production process due to acknowledged accent and pause errors.
ProcessesCheck the original
Event sources
confirmed by 2 independent sources · 2 publishers, 2 independent. We count feeds from the same owner only once.