Models · 1 October 2026 · 1 min read
Suno Speech: a voice and its music in one take
Open to all from 1 October 2026: describe a voice and a musical style, and the speech and its soundtrack come out as one track.
By The Crewnema team
Suno opened Speech, in beta, to all users on 1 October 2026, after about a month with a small group. Suno describes it as the first model to generate voice and music together as one track. These are the points from Suno’s announcement.
What Suno announced
- Spoken audio and original background music generated together, in one take.
- You give an idea or your own words, then describe the voice and the musical style.
- Available in the Suno app on Android, iOS and the web.
- Beta behaviour, in Suno’s words: a British accent can drift towards Australian and back, and dramatic pauses can be very dramatic.
Suno did not publish languages, length limits or pricing for Speech.
Our view
Voice and music made together should sit better than a voice laid over a separate track: the music can leave room for the words. That is what a radio spot or a reel voiceover needs. Two things stop us recommending it for adverts yet. It is an app, not a service another product can call, and the drifting accent Suno mentions is exactly what a brand voice cannot have. We would also want a separate voice track: in an advert you often change the music and keep the words.
Side by side
In Crewnema
Suno Speech is not on Crewnema’s roster. In Crewnema the voiceover and the music are made separately and mixed in the export, with the music kept under the voice, so either can be changed without the other.
Sources
Make your first video
Crewnema is in private beta and lets businesses in a few at a time. Request access and we will write when yours is open.