Suno leans into customization with v5.5 | The VergeSkip to main contentThe homepageThe VergeThe Verge logo.The VergeThe Verge logo.TechReviewsScienceEntertainmentAIPolicyHamburger Navigation ButtonThe homepageThe VergeThe Verge logo.Hamburger Navigation ButtonNavigation DrawerThe VergeThe Verge logo.Login / Sign UpcloseCloseSearchTechExpandAmazonAppleFacebookGoogleMicrosoftSamsungBusinessSee all techReviewsExpandSmart Home ReviewsPhone ReviewsTablet ReviewsHeadphone ReviewsSee all reviewsScienceExpandSpaceEnergyEnvironmentHealthSee all scienceEntertainmentExpandTV ShowsMoviesAudioSee all entertainmentAIExpandOpenAIAnthropicSee all AIPolicyExpandAntitrustPoliticsLawSecuritySee all policyGadgetsExpandLaptopsPhonesTVsHeadphonesSpeakersWearablesSee all gadgetsVerge ShoppingExpandBuying GuidesDealsGift GuidesSee all shoppingGamingExpandXboxPlayStationNintendoSee all gamingStreamingExpandDisneyHBONetflixYouTubeCreatorsSee all streamingTransportationExpandElectric CarsAutonomous CarsRide-sharingScootersSee all transportationFeaturesVerge VideoExpandTikTokYouTubeInstagramPodcastsExpandDecoderThe VergecastVersion HistoryNewslettersArchivesStoreVerge Product UpdatesSubscribeFacebookThreadsInstagramYoutubeRSSThe VergeThe Verge logo.Suno leans into customization with v5.5Comments DrawerCommentsLoading commentsGetting the conversation ready...EntertainmentCloseEntertainmentPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All EntertainmentAICloseAIPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All AINewsCloseNewsPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All NewsSuno leans into customization with v5.5Its latest AI music-making model can be trained on your own voice and songs.Its latest AI music-making model can be trained on your own voice and songs.by Terrence O'BrienCloseTerrence O'BrienWeekend EditorPosts from this author will be added to your daily email digest and your homepage feed.FollowFollowSee All by Terrence O'BrienMar 28, 2026, 6:33 PM UTCLinkShareGiftSlop yourself. Image: SunoTerrence O'BrienCloseTerrence O'BrienPosts from this author will be added to your daily email digest and your homepage feed.FollowFollowSee All by Terrence O'Brien is the Verge’s weekend editor. He has over 18 years of experience, including 10 years as managing editor at Engadget.Suno just released one of its biggest updates yet with v5.5 of its AI music model. Where previous updates focused mostly on improving fidelity and creating more natural vocals, v5.5 is about giving users more control. It includes three new features: Voices, My Taste, and Custom Models.In the release notes, Suno says that Voices is its most requested feature. It lets users train the vocal model on their own voice. They can upload clean accapellas, finished tracks with backing music, or just sing directly into the mic on their phone or laptop. The cleaner and higher quality the recording, the less data is required. And to prevent someone from simply stealing another person’s voice, Suno requires the user to also speak a verification phrase. Though, this might be possible to fool with existing AI models of celebrity voices.Once the Voices feature is trained, users can then have an AI version of themselves sing on uploaded music or AI-generated outputs.To further personalize outputs, Custom Models allows users to train Suno on their own music. Users will need to upload at least six tracks from their catalog and give the custom model a name. Then they’ll be able to use it to guide v5.5 responses to prompts.Lastly, My Taste learns tastes and preferences over time. What genres, moods, and artists you routinely come back to for prompts, and applies them when using the magic wand to autogenerate styles.While My Taste will be available to all users, Voices and Custom Models are reserved for Pro and Premier subscribers.Follow topics and authors from this story to see more like this in your personalized homepage feed and to receive email updates.Terrence O'BrienCloseTerrence O'BrienWeekend EditorPosts from this author will be added to your daily email digest and your homepage feed.FollowFollowSee All by Terrence O'BrienAICloseAIPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All AIEntertainmentCloseEntertainmentPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All EntertainmentMusicCloseMusicPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All MusicNewsCloseNewsPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All NewsTechCloseTechPosts from this topic will be added to your daily email digest and your homepage feed.FollowFollowSee All TechMost PopularMost PopularReturning from a humanitarian aid trip to Cuba, Americans have phones seized at US airportSony is raising PS5 prices by $100 in AprilRank the 50 best Apple productsAnker’s 160W Prime Charger can power three devices at once, and it’s $50 offMeta gets ready to launch two new Ray-Ban AI glassesThe Verge DailyA free daily digest of the news that matters most.Email (required)Sign UpBy submitting your email, you agree to our Terms and Privacy Notice. This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.Advertiser Content FromThis is the title for the native adMore in EntertainmentA classic Zelda-style adventure, but a lot more cozyThe photo mode consultant helping you take better video game screenshotsApple’s AI Playlist Playground is bad at musicStreaming keeps getting more expensive: all the latest price hikesNetflix is raising prices againXbox’s latest games showcase had Hades 2, The Expanse, and BlueyA classic Zelda-style adventure, but a lot more cozyAndrew Webster1:00 PM UTCThe photo mode consultant helping you take better video game screenshotsKhee Hoon ChanMar 27Apple’s AI Playlist Playground is bad at musicTerrence O'BrienMar 26Streaming keeps getting more expensive: all the latest price hikesVerge StaffMar 26Netflix is raising prices againEmma RothMar 26Xbox’s latest games showcase had Hades 2, The Expanse, and BlueyAndrew WebsterMar 26Advertiser Content FromThis is the title for the native adTop StoriesMar 27Rank the 50 best Apple products2:00 PM UTCMeta’s legal defeat could be a victory for children, or a loss for everyone11:00 AM UTCOppo made the best foldable phone, again12:00 PM UTCWhy OpenAI killed Sora12:00 PM UTCThe must-have app for frequent flyers2:00 PM UTCWhy can’t TikTok identify AI generated ads when I can?The VergeThe Verge logo.FacebookThreadsInstagramYoutubeRSSContactTip UsCommunity GuidelinesArchivesAboutEthics StatementHow We Rate and Review ProductsCookie SettingsTerms of UsePrivacy NoticeCookie PolicyLicensing FAQAccessibilityPlatform Status© 2026 Vox Media, LLC. All Rights Reserved

Suno has introduced version 5.5 of its AI music generation model, marking a significant shift toward enhanced user customization and control. This update, driven by a response to user requests, diverges from previous iterations which primarily focused on improving the fidelity and naturalness of AI-generated vocals. The core advancements introduced in v5.5 center around three key features: Voices, My Taste, and Custom Models.

The “Voices” feature represents a substantial development, enabling users to train the AI model to replicate their own voice. This process involves uploading audio – whether in the form of clean vocal isolations, finished tracks with backing music, or direct recordings via a microphone – with the quality of the recording influencing the amount of data required for training. Crucially, Suno implements a verification phrase requirement alongside voice training to mitigate the potential for unauthorized voice cloning. Despite this safeguard, the possibility of exploiting existing AI models to mimic celebrity voices remains a concern. Once trained, the “Voices” feature allows users to generate AI versions of themselves singing alongside music, or even in newly created AI-generated outputs.

Furthermore, “Custom Models” provide users with the ability to train Suno on their own musical catalogs. This functionality necessitates uploading a minimum of six tracks from a user’s existing collection, coupled with a designated name for the custom model. This enables users to guide Suno’s responses to prompts using their particular musical style and preferences. This customization adds a layer of complexity to the tool, allowing for greater consistency and fidelity to a user’s established creative work.

Finally, “My Taste” learns a user’s musical inclinations over time. This feature monitors the genres, moods, and artists a user repeatedly engages with as prompts, and then applies these preferences when the “magic wand” feature automatically generates styles. This feature is broadly available to all users, while “Voices” and “Custom Models” are restricted to subscribers of the Pro and Premier tiers.

Essentially, Suno v5.5 is designed to move beyond merely generating realistic vocals, fundamentally reshaping the user experience through personalization and control. The developers, led by Terrence O'Brien, have deliberately responded to user demand, shifting the emphasis to empower users to directly shape the creative output of the AI, representing a proactive strategy to maintain relevance within the rapidly evolving landscape of AI music generation.