Suno v5.5 adds voice training, custom models, taste AI
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- Suno released version 5.5 of its AI music model, the biggest update yet, focusing on user control.
- Voices lets users train the vocal model on their own voice by uploading clean acapellas, finished tracks, or singing directly, and requires a verification phrase to prevent misuse.
- Custom Models enables users to train Suno on at least six of their own tracks, naming the model, to guide v5.5 responses to prompts.
- My Taste learns a user’s preferred genres, moods, and artists over time and applies them when auto‑generating styles with the magic wand.
- Voices and Custom Models are only accessible to Pro and Premier subscribers.
- My Taste is available to all users at no extra cost.
Why it matters: Pro and Premier users now can embed their own vocal timbre and musical catalog into Suno’s AI, giving them exclusive, personalized song generation, while all users benefit from automated style recommendations via My Taste. The tiered rollout deepens the value gap between paid and free plans, prompting creators to upgrade for full customization.
