Suno Unveils v5.5 Update, Adding Voice Cloning, Personalized Tasting, and Custom Music Models

Suno has launched version 5.5 of its AI music model, shifting focus from pure fidelity improvements to user‑driven customization. The update introduces three new tools—Voices, My Taste, and Custom Models—that let creators train the system on their own vocal timbre, learn individual genre preferences, and tailor the model to specific music catalogs. While My Taste is available to all users, Voices and Custom Models are limited to Pro and Premier subscribers. The rollout promises a more personal and controllable AI‑generated music experience.

Overview of the v5.5 Release

Suno announced the most significant update to its AI music platform to date with the launch of version 5.5. Unlike earlier updates that primarily enhanced sound fidelity and natural vocal rendering, v5.5 is built around user control and personalization. The company highlighted three new features—Voices, My Taste, and Custom Models—that collectively give musicians, producers, and hobbyists deeper ways to shape AI‑generated output.

Voices: User‑Generated Vocal Cloning

The Voices feature fulfills the most requested demand from Suno’s community. It enables users to train the vocal model on their own voice by uploading clean a cappella recordings, finished tracks that include backing instrumentation, or raw vocal takes recorded on a phone or laptop. Higher‑quality recordings reduce the amount of data needed for training. To mitigate misuse, Suno requires a verification phrase spoken by the user, although the source notes that existing AI models could potentially bypass this safeguard.

Once a personal voice model is created, users can have an AI version of themselves sing over uploaded music or generate entirely new vocal tracks, expanding creative possibilities without needing to record every performance.

Custom Models: Tailoring the Music Engine

Custom Models extends personalization to the broader musical style of a creator’s catalog. Users must provide at least six tracks from their own body of work and assign a name to the new model. After training, the custom model influences how v5.5 responds to prompts, allowing the AI to generate music that aligns closely with the creator’s established sound.

My Taste: Adaptive Genre and Mood Recommendations

My Taste learns a user’s recurring preferences—such as favored genres, moods, and artists—by analyzing the prompts they repeatedly select. The system then applies these insights when the “magic wand” tool auto‑generates styles, delivering outputs that match the user’s habitual tastes. Unlike Voices and Custom Models, My Taste is available to all Suno users without subscription restrictions.

Subscription Tier Distinctions

The new features are rolled out with tiered access. Both Voices and Custom Models are reserved for Pro and Premier subscribers, reflecting their more advanced capabilities and the additional resources required for model training. My Taste remains a universal feature, ensuring that even free‑tier users benefit from personalized recommendations.

Implications for the AI Music Landscape

By shifting emphasis toward customization, Suno positions itself as a platform that empowers creators to retain artistic ownership while leveraging AI efficiency. Voice cloning and catalog‑specific modeling address long‑standing concerns about generic AI output, while the adaptive taste engine streamlines the creative workflow. The update signals an industry trend toward hybrid solutions that blend machine intelligence with human‑driven direction.