I tried Suno Studio the new platform that mixes AI music generation with hands-on editing – like GarageBand, but smarter

Suno Studio
(Image credit: Suno)

AI song creator Suno has gone beyond simply turning prompts into tunes. With the new Suno Studio platform, creators can now start from scratch and use AI to break down and edit their tracks, combining what might be called GarageBand-style editing with AI-fueled music generation.

Suno calls the platform the “world’s first generative audio workstation,” and it's not a bad way to describe it. Though at first glance Suno Studio offers the conventional options of a digital audio workstation (DAW) like Pro Tools or GarageBand, you don't need pre-recorded audio, MIDI knowledge, or access to virtual instruments to make a tune. You can start with the roughest of rough ideas and grow an entire track around it using AI.

You do need to pay up for the privilege of access, though. Suno Studio is currently available on desktops only, for Premier subscribers. That's $30 a month, three times the cost of a Pro subscription (prices are slightly lower if you go for the yearly payment). Still, combined with the release of its new v5 music model, there could be a lot of potential for Suno to go from a viral novelty to a serious creative tool.

Suno Studio – The first-ever generative audio workstation - YouTube Suno Studio – The first-ever generative audio workstation - YouTube
Watch On

Essentially, it mimics the standard music platforms, but you don’t have to drag in a beat; you can just generate one. You can adjust the pitch, tempo, and volume. You can isolate the vocals or replace the snare. You can also use regular (musical) language to play with the sound, whether you want to tell it to “make the synth sound more dreamy” or to “give me a funky bassline in 6/8." Then you can keep tweaking, editing on a multitrack timeline, exporting as audio or MIDI, and dropping those elements into any other production environment.

You don’t have to come to the table with a nearly complete song, like with most music editing software. Whatever fragments or moods you have are enough to start with. Even just humming can make for a foundation for a song. Suno Studio will offer all the drum patterns or chord progressions you could desire.

From a technical standpoint, Suno Studio softens the input requirements of text prompts or pre-rendered audio. The line between composition and AI generation is blurrier. And you can tell Suno wants to appeal to both hobbyists and professionals with the features familiar to GarageBand and Pro Tools users.

And while Suno allows you to edit and refine, it’s not yet capable of deep customization. For instance, you can’t tell it to mimic a specific player’s phrasing or perform a solo in the style of your favorite local pianist. That’s likely by design. Suno says Studio should be a collaborator, not a way to rip off artists.

Experimental Studio

I decided to play around with making songs using Suno Studio. I started by asking for an upbeat pop song, then used the remix tool to give it a 50s rock and roll vibe and make it a summer hit about dancing and sunshine. The lyrics it generated were pretty on-the-nose about it, but it wasn't bad. I used Studio to play with the stems, swapping out the drums from it with the drumbeat from another prompt result and cutting out one of the two effects tracks. It was pretty easy, I have to admit, though whether the result is impressive or irritating is subjective.

I then wanted to see how specific I could make the sound and asked for a “1980s-style synthwave track with a dramatic saxophone solo. The song should be about driving through the night.” I wasn't too impressed with most of what came out, but I did like the bass beat and the sound of the singer's voice, so I pulled those stems out and told Suno Studio to make another song with those sounds. Though the lyrics weren't ideal, I decided Neon Highway was ready to share.

For my last test, I went with something instrumental. I wanted to see if I could feel inspired by the music from Suno v5 after some tweaking in Suno Studio. I asked for a dynamic, epic orchestral superhero theme with plenty of brass and energy. For some reason, despite multiple attempts at remixing and moving around different stems, the result always felt at least a little generic. Like if Alan Silvestri or Michael Giacchino really phoned it in for the next Marvel movie.

In each case, I noticed the songs didn’t start to feel alive until I got involved. And I know that if I really wanted to get them to make people feel things, I would have to do more, whether with the lyrics or the saxophone solo or even just a bass beat to make it feel less mechanical. I came away with three songs I could probably play for a stranger without being too embarrassed. That’s not nothing. But it’s also not musical magic.

Suno sounds out the mood

Impressive as Suno Studio is as a potential professional toolkit, it does face certain challenges its rivals don't, as a result of the same AI that makes it unique. The company is currently facing lawsuits from major music labels alleging that it trained its models on copyrighted material without consent, including YouTube streams and other publicly available music. If courts side with the labels, it could limit what kinds of generative AI audio will be legal as a commercial product, and thus how attractive Suno Studio is to working musicians.

And the aesthetic debate raised by my own experiments might make it a moot point. Even if it’s legal, is it good? There are many who find AI music generators to be limited to technically polished but emotionally shallow tracks. As I found, the lyrics don’t always make sense, and the work to blend various bits of AI-generated sound you like can be prohibitive compared to simply having a great singer or musician in the studio ready to lay down another track.

Of course, the easier it becomes to make music, the more music of all qualities could flood people's ability to listen. There are 100,000 tracks uploaded per day to Spotify. If generative music tools dramatically increase that volume, discoverability could plummet further. There’s also the risk of homogenization. AI models are trained on existing music. If millions of users begin creating new music using outputs from those models, we may end up in a cultural feedback loop of derivative music feeding more derivative music. Even if some of those AI-created songs do lead to huge record deals.

Personally, I think Suno Studio could be a great help to artists who know what they are doing. Using it to play with different stems or brainstorm ideas makes sense. If you want to use it as a one-click hitmaker, you might not be as satisfied. Nonetheless, if you have an idea and a computer, you can have something approximating a full song in minutes. Whether that song is meaningful or good is still up to you.

You might also like

TOPICS
Eric Hal Schwartz
Contributor

Eric Hal Schwartz is a freelance writer for TechRadar with more than 15 years of experience covering the intersection of the world and technology. For the last five years, he served as head writer for Voicebot.ai and was on the leading edge of reporting on generative AI and large language models. He's since become an expert on the products of generative AI models, such as OpenAI’s ChatGPT, Anthropic’s Claude, Google Gemini, and every other synthetic media tool. His experience runs the gamut of media, including print, digital, broadcast, and live events. Now, he's continuing to tell the stories people want and need to hear about the rapidly evolving AI space and its impact on their lives. Eric is based in New York City.

You must confirm your public display name before commenting

Please logout and then login again, you will then be prompted to enter your display name.