Suno 5.5 lets users sing their own AI-generated songs with a personalized voice feature
Key Points
- Suno has released version 5.5 of its AI music generator, introducing three new features designed to make music creation more personal: Voices, Custom Models, and My Taste.
- The Voices feature allows Pro and Premier subscribers to record or upload their own vocals, which can then be used as the singing voice in AI-generated songs.
- All three new functions share a common goal: tying the music generation process more closely to each user's individual identity and preferences, rather than producing generic AI output.
AI music company Suno has released version 5.5 of its music generator. Beyond improved sound quality, users can now sing with their own voice and train the model to match their personal style.
Suno has unveiled version 5.5 of its music model, which the company calls its "best and most expressive model yet." The update centers on three new features: Voices, Custom Models, and My Taste. All three are designed to make music creation feel more personal.
According to Suno, these features will "lay the foundation for the next generation of music models we're launching with the music industry later this year." Suno slips that in casually, but it's a hint at how the startup's legal battles might be going: the company is currently fighting lawsuits from major record labels, and competitor Udio has already been more or less swallowed up by Universal Music Group.
Users can now sing their own AI-generated songs
Suno says Voices is the most requested feature from its community. Available to Pro and Premier subscribers, it lets users record or upload their own vocals and use them to generate songs.
To prevent misuse, Suno built in a verification step: the singing voice in the uploaded audio is matched against a randomly generated speech phrase that the user has to record. This makes sure only the user's own voice gets used.
Voice profiles are private by default. Suno says it plans to add a sharing option down the road, with users keeping full control over their voice data.
Custom Models and My Taste shape the sound to fit each user
With Custom Models, Pro and Premier subscribers can fine-tune the v5.5 model using their own music. Upload tracks from a personal catalog, and Suno creates a personalized version of the model that picks up on individual style and works it into new compositions. Users can create up to three custom models.
My Taste is open to all users: Suno picks up on which genres and moods someone gravitates toward over time and adjusts its output to match.
AI News Without the Hype – Curated by Humans
As a THE DECODER subscriber, you get ad-free reading, our weekly AI newsletter, the exclusive "AI Radar" Frontier Report 6× per year, access to comments, and our complete archive.
Subscribe now