Suno Opens Speech to Everyone in Beta, Combining Synthetic Voice and Music in One Track
Suno has made its Speech feature available in public beta. The tool creates spoken audio with original background music and supports both an idea prompt and a custom script.
Suno Speech beta has been available to all service users on the web and in the mobile app since October 1. The new feature creates spoken audio with originally generated background music in one final track.
Speech expands Suno’s use to formats centered on spoken delivery—for example, commentary, poetry, meditations, and short audio formats with musical accompaniment.
Suno Speech beta after a month-long test
According to an announcement from Suno, the feature underwent a month-long test with a smaller group of users before its public launch. The company has now opened it to everyone in beta.
Users can enter a brief idea or their own text and then describe the voice and musical style they want to use in the output. Speech is intended to create the spoken part and musical background together, rather than as two separately prepared elements.
Suno describes Speech as the “first audio model” to generate voice and music as a unified track. However, this is a marketing claim by the manufacturer that has not been independently verified.
Script, voice, speaking style, and variability
According to The Verge, Speech is available in both the web and mobile versions of Suno. The feature offers a simpler idea-based workflow as well as an advanced mode for more precise input.
In advanced mode, users can enter a full script and adjust the voice’s gender, speaking style, and degree of variability.
The maximum length of generated audio is approximately eight minutes, according to The Verge.
Beta version has acknowledged limitations
Suno warns that Speech is still a beta feature and that results may not be the same with every generation. The company specifically mentions inconsistent accents and exaggerated pauses in speech.
Unclear availability and voice protections
Based on the available information, it is unclear in which countries Speech is accessible, which Suno pricing plans include the feature, or what usage limits apply. The available materials do not clarify what specific technical or policy protections against imitation and misuse of synthetic voices apply to this feature.
As development continues, it will therefore be important to see whether the company publishes these rules and measures, how it sets availability and pricing, and what results independent testing of longer generated recordings produces.
Sources
- Suno Blog — Introducing Speech (beta) – Confirms the announcement of Speech, its purpose, the method for entering text and style, the preceding month-long test, and the opening of the beta to everyone.
- The Verge — AI music maker Suno now generates spoken words – Independently describes public beta availability on the web and mobile, creation modes, controls, and the approximate eight-minute length limit.
Verified and updated: 10/02/2026 15:25
