Suno V4: A Leap Forward in AI Music Generation

Suno's upgraded AI song generator might get even skeptics' toes tapping

Become a 21st-century Barry Gordy with AI singers and lyricists AI song creator Suno has opened the doors to a new virtual studio, releasing the Suno v4 platform for music creation. The much-teased upgrade lets users make better, longer, more creative songs and is looking to attract professional artists and producers interested in incorporating AI into music-making. "When we launched v3 earlier this year, it opened up new possibilities for music creation. Post v3 launch, we've refined what worked and added more where it mattered most," Suno wrote in a blog post. "The result is v4 -- a major update that takes music creation to the next level. v4 delivers cleaner audio, sharper lyrics, and more dynamic song structures." The change is obvious just by hearing how synthetic voices sound on Suno v4. The improved vocal clarity and tone are no longer stuck in the audio uncanny valley. They sound like real people. And, if you made a song with the older versions of the platform, you can use the new Remaster tool to enhance the track to match the new level of quality while keeping all of the elements you like. Suno v4 also has new user tools that will likely encourage extended use. The Personas feature takes those new, improved voices and makes them part of your library. Essentially, you can apply an AI voice you like to any song you create. The consistent singing style across multiple tracks means you could theoretically create whole albums starring a single voice you like, as though the artificial voice were a singer you had under contract. Furthermore, you'll have better lyrics for your virtual client to perform with the new lyric model called ReMi, which is available in the custom creation mode. ReMi gets a little quirkier than the usual lyrics, pushing creativity over adherence to more conventional songwriting. It definitely makes for more unpredictable songs, which may or may not be ideal for producing the song you want. The upgrade also takes the Covers feature out of beta. Covers is a tool that reinterprets your songs in new genres. So, if you generated a fun pop song but wanted to hear it performed like an old Scottish folk song or maybe sung to a dubstep beat, you can hear how that sounds. Suno v4's appeal to both casual music lovers and professional musicians makes sense. This kind of technical wizardry may be crucial as Suno faces many rivals, including Tad.AI, Udio, and Boomy. Suno's mobile app and features like Scenes, which writes songs based on uploaded visuals instead of written prompts, will be necessary to stand out. You can try Suno v4 now, though whether it will survive the ongoing lawsuits Suno and other AI music platforms face from major music labels for copyright infringement is still unclear.

Suno v4 is out and this AI music generator is even better than I expected -- listen for yourself

Suno, one of the leading artificial intelligence music generators has finally released the much anticipated v4 model. This brings with it longer songs, improved tone and a much more natural sounding vocal across a range of genres. The AI startup first went public with its original model in December last year as a plugin inside Microsoft Copilot. It was one of the first to combine music and vocals creating a full song. The release of v3 in March this year was the breakout moment. One of the biggest issues with the earlier model came from the slightly robotic tone vocals. Version 4 has completely changed this, creating songs indistinguishable from human performances. The new release comes as Suno faces lawsuits from Sony Music Entertainment, Warner Music Group and the Universal Music Group. They accuse Suno and competitor Udio of allegedly training the underlying model on copyrighted music without authorization. Suno says this was "fair use" under U.S. copyright law. Scroll down for examples of Suno v4 tracks inspired by the Tom's Guide team. Suno v4 isn't just an upgrade to the vocals and overall sound quality; the startup has also been working on related features such as covers and personas. Personas allows you to create a custom vocalist based on previously generated songs, ensuring you have a consistent singing style across tracks. This now works with v4 and so the vocal will be clearer. Covers, which were previously limited in terms of the number of uses, allow you to take a sound you've uploaded or another Suno track and create a new version. I used this to create a full song from a riff I'd had in my head for years. Suno has also dropped Remaster, a new feature that lets you enhance a track you made with an older model to upgrade it to v4 quality. Finally, there is a new lyric model that comes with v4 called ReMi. It is only available under 'custom mode' and it is much more creative, and unhinged than the earlier version of Suno's lyric model -- which is still accessible and the default. Here is an example of a track made in Suno v4 called Rust Never Sleeps It took multiple attempts to get it to make this song in the "Grunge" genre specified by Tom's Guide How To Editor Kaycee Hill. Every previous attempt came up with a country style. I decided to regenerate the lyrics using a more defined prompt as just putting "Rust Never Sleeps" and "Grunge" for some reason was interpreted by Suno v4 as good ol' boy country rock. This track made in Suno v4 is in the Rock genre and called Winner Stays On This was a title and genre suggestion from Tom's Guide UK Editor-in-Chief Jeff Parsons. It was made using a simple text prompt "Rock song with the title Winner Stays On" and then adapted to use the Epic Rock genre for a better output as the others sounded to 'country'. This track from Suno v4 was made when I was barely awake and called Foggy Mornings I woke up for work amid the flu and my first thought was "my brain isn't braining this morning" so I put just that into Suno v4's ReMi lyric generator and left it to do its thing. I didn't specify a genre. Suno v4 is a bigger step up in realistic music generation than any previous model has achieved. After a minute or so you can easily forget it is an AI track you generated yourself. This is going to allow anyone with an idea to create a song for a loved one, a track for a marketing video or music for a video game. Forget AI playlists, this will allow you to create your own Thanksgiving songlist where each song is customized for a member of your family visiting. Maybe don't use the unhinged ReMi lyric generator when you're writing about that slightly suspect uncle that nobody really wants to visit. As Suno warns it: "May generate content that some find offensive".

Suno V4 AI Music Generator Released

Suno V4 has just been released and marks a significant leap forward in AI music generation, introducing superior quality and new features that push the boundaries of what's possible in computer-generated audio. This latest release improves voice clarity and song consistency, setting a new benchmark for AI-generated music and opening up exciting possibilities for creators and music enthusiasts alike. "Today, we're excited to introduce v4 -- the next step toward enabling you to make music at the speed of your ideas. When we launched v3 earlier this year, it opened up new possibilities for music creation. Post v3 launch, we've refined what worked and added more where it mattered most. The result is v4 -- a major update that takes music creation to the next level. v4 delivers cleaner audio, sharper lyrics, and more dynamic song structures." Sun v4 comes with a pack of new, exciting features along with upgrades to popular features like Covers and Personas. As well as another lyrics assist option designed to help you write more creative lyrics and elevate your songwriting. With Suno V4, you experience a substantial upgrade in voice quality compared to earlier versions. The sound is noticeably clearer and more natural, enhancing the overall listening experience and bringing AI-generated vocals closer to human-like quality. Improvements in song structure and melody consistency ensure a more cohesive musical output, addressing previous limitations in AI-generated compositions. The advancements in Suno V4 include: These enhancements collectively contribute to a more polished and professional-sounding end product, bridging the gap between AI-generated and traditionally produced music. A standout feature of Suno V4 is the Persona function, which maintains consistent character voices throughout a track. This is particularly valuable for projects that require distinct vocal identities, such as concept albums or narrative-driven musical pieces. The Persona function allows for greater creative control and opens up new possibilities in storytelling through music. Moreover, the ability to remaster older Suno tracks into V4 is a fantastic option for users with existing projects. This feature allows your previous creations to benefit from the latest audio quality advancements, breathing new life into older works and making sure they meet current standards of AI-generated music. To fully access Suno V4's capabilities, a Pro Plan subscription is necessary. This unlocks the platform's complete potential, giving you access to: Engaging with the community via Discord enables you to share and discuss your creations, fostering a collaborative environment. This interaction not only enriches your experience but also contributes to the platform's continuous evolution. By participating in discussions, sharing tips, and showcasing your work, you become part of a vibrant ecosystem of AI music creators. Despite its significant advancements, Suno V4 is not without limitations. Certain audio quality issues persist, particularly with high-pitched notes, which can affect the overall sound in some compositions. Users should be aware of these constraints when working on projects that heavily feature high vocal ranges or intricate harmonies. Additionally, the AI-generated lyrics may occasionally appear humorous or nonsensical, introducing an unpredictable element to the music. While this can lead to creative and unexpected results, it may require additional editing or human intervention for more serious or professional projects. Discover other guides from our vast content that could be of interest on AI music generation. The active participation of the community is vital to the ongoing development of Suno V4. By testing and providing feedback, users help refine the platform, making sure it meets the creative needs of its audience. This collaborative effort allows you to: The feedback loop between users and developers is crucial in addressing limitations and expanding the capabilities of Suno V4, making it a dynamic and evolving tool for music creation. As Suno V4 continues to evolve, its impact on the music industry could be significant. The technology has the potential to: While Suno V4 represents a major advancement in AI music generation, it's important to view it as a tool that complements human creativity rather than replacing it. The platform offers new creative possibilities while recognizing areas that still need improvement. As you explore Suno V4's capabilities, you will discover a tool that not only enhances your musical projects but also invites you to be part of a dynamic, evolving community at the forefront of AI-driven music creation. Whether you're a seasoned musician looking to expand your creative palette or a curious enthusiast eager to experiment with innovative technology, Suno V4 offers a unique and exciting platform to explore the future of music production.

AI Music Is More Realistic Than Ever: Meet Suno's New Model

Attack of the David Attenborough AI Clones: 'My Identity Is Being Stolen' Even as it faces a lawsuit from the recording industry for using countless copyrighted songs to train its music-generating AI model, Suno has become the fifth most-used generative-AI service in the world -- and the company is still pushing its technology forward. A new, notably more realistic model, V4, is available today to paid subscribers, and will eventually reach all users. "I think it crosses into something I actively want to listen to," says Suno co-founder Mikey Shulman. "Instead of, like, something that I want to keep making it better." Shulman is sitting in a brand-new studio space, complete with actual guitars, basses, and a high-end sound system, in the company's equally new custom-built offices, which take up two floors -- soon to be three -- right by the Harvard University campus in Cambridge, Mass. "We had to make the model better to justify having bought the fancy speakers," Shulman jokes. As of February, the company had 12 or so employees; now they're up to more than 50, with more to come. "It's hard to compete with OpenAI for really talented researchers," says Shulman, referring to the AI giant behind ChatGPT. "But the way we compete is if you want to learn to align [AI] models with human taste, there's no better place to do it." Unlike large language models, which have objective benchmarks -- you can compare Claude and ChatGPT's scores on the LSATs, for instance -- Suno's engineers can only use human preferences. Taking note of past users' preferences between different results from the same prompt has played a substantial role in improving the new model. "Just after a few more months of being able to do that, we have better ideas of what human preferences are," Shulman says. AI-generated music, whether from Suno or its most direct competitor, Udio, tends to have a certain tinniness -- not unlike low-bitrate MP3s -- that's most evident in the vocals. As we generate song after song over a couple hours in the studio, V4's productions are crisper than any previous Suno model could muster, with more realistic singers and instrumentation, plus a broader stereo field. Shulman says that the model has improved its composition skills as well. "The music is getting more interesting," he argues. "You're getting chord changes you didn't expect." In one of our efforts, which you can hear above, we used a set of lyrics I quickly wrote, paired with a prompt for "organic country," with fairly impressive results -- you can practically see the worn hat on the nonexistent vocalist. That vocalist does sound notably Auto-Tuned, which may reflect the number of electronically enhanced vocals in Suno's training data. For AI-music's opponents -- a category that officially speaking, at least, includes almost the entire recording industry and its artists, many of whom have signed anti-AI petitions -- the prospect of an even more capable music-generating AI isn't good news. There are exceptions, though: Timbaland, for one, recently told Rolling Stone he's using Suno "10 hours a day" to finish incomplete songs, and has partnered with the company as a creative consultant. And Shulman insists he's hearing from numerous artists, songwriters, and producers who are quietly using Suno, including at least one A-lister who Shulman says signed an anti-AI petition. Shulman hopes some agreement can be reached about the use of training data, but also thinks artists should be more worried about models that can eventually reproduce their voices even if they're not trained on them -- something Suno doesn't allow, since artists' names are prohibited from prompts. "Somebody is going to train a model without any Neil Young in it," says Shulman. "And then figure out how to prompt a spitting image of Neil Young out of that model by describing it correctly." Suno's capabilities have gone well beyond ChatGPT-style text prompts -- you can now upload your own partial compositions, a cappella vocals, loops, or other audio and turn it into songs, in an advanced level of human-AI collaboration. (They also have a beta feature that lets you upload videos or photos to inspire songs.) Rebecca Hu, a project manager for Suno, says the ability to iterate from existing audio is attracting young beatmakers to the platform. "A lot of our power users are young producers," says Hu. "They think this is the future.... We're trying to move to a music-based UI. Text is hard to understand when it comes to music.... I think the interesting use cases are producers or songwriters in a room, iterating." Still, the company is mostly focused on its original mission of getting non-musicians involved in making music. V4 also comes with an option to use a new, in-progress lyric-generating model the company is working on, which generates quirkier and more human-seeming lyrics than its previous use of ChatGPT's model. It's notably better at generating rap lyrics, though it does bite a line from Drake circa 2015 -- "running through the Six" -- in one of our demos. The copyright lawsuit looming over Suno isn't on the minds of most employees, Shulman says, but it "obviously affects things, It's not good to to get sued. But I think there is a future of music that we are excited about building. And viewed in that light, this is a speed bump, but should not ultimately get in the way of everybody building that future of music." He adds that he wants to eventually enlist labels and artists as partners: "That future of music, we actually can't and don't want to do by ourselves."