Image Credit: Suno and Udio 

Generative AI Music has been making (sound) waves for a while now, but recently it’s become a full fledged tsunami. With AI generated songs like BBL Drizzy being sampled by Metro Boomin for use in the rap beef between Kendrick and Drake, as well as artists like Obscurest Vinyl using AI generated music to garner massive social media and streaming numbers, the floodgates appear to be wide open. 

The two biggest players in the Generative AI “text to song” space are Suno and Udio. Both platforms have an easy to understand interface where users can simply type in a mood, concept, genre, and even custom lyrics to generate a fully produced song with compelling vocals and epic instrumentals. If you don’t write lyrics, they will even write lyrics for you based on your prompt. 

Most recently, both platforms also introduced “Audio to Audio” functionality where users can input a sound, loop or sample and have the AI craft a full fledged song using the original sound. In a lot of ways, it feels like magic. 

In this article, we are going to explore both AI Music platforms in depth. By comparing interfaces, quality, features, and cultural impact, we aim to get one step closer to determining what the future of AI Music looks like, and deem the “King of Generative AI Music”… for now. Let’s dive in. 

User Interface

Suno: Suno AI boasts an intuitive and user-friendly interface designed to simplify the music creation process. Users can easily input text prompts, select musical styles, and generate songs. The platform is accessible via its web interface, Discord, and Microsoft Copilot, allowing for flexible use across different environments. Suno’s interface is praised for its modern design and ease of use, making it suitable for both beginners and experienced musicians.

Image Credit: Suno

Udio: Udio also offers a user-friendly interface, focusing on clarity and simplicity. It allows users to generate music with minimal effort, providing straightforward controls and options. Udio also allows for audio inpainting, which allows for a seamless way to easily edit and refine the music it produces. The platform is particularly appreciated for its clean layout and intuitive design, which helps users navigate the music creation process smoothly.

Image Credit: Udio

Quality of Sound

Suno: Suno’s latest model, Suno 3.5, excels in generating imaginative and genre-blending compositions. It is capable of producing complex musical pieces that often defy conventional structures. In our tests, the outputs are powerful and compelling with creative compositional elements. However, sometimes when writing custom lyrics, Suno has a tendency to over exaggerate syllables leading to some fairly odd sounding vocal melodies. 

Udio: Udio is known for its high audio fidelity and technical precision. It consistently delivers clean, artifact-free audio and excels in producing rich, harmonically complex compositions. The clarity and balance it achieves is impressive, but perhaps the most intriguing aspect of its generations are the tasteful effects it adds to different elements within the “mix”. These intricacies make the generations feel intimidatingly human, and in our experience, make them extremely fun to listen to. 

Prompt Accuracy

Suno: Suno’s ability to interpret and execute text prompts is highly regarded. It can generate music that aligns closely with the specified genres, moods, and styles provided by the user. The creativity of the types of prompts it allows is also a great deal of fun, with users being able to create never before heard genres such as “Norwegian Folk Metal” or “Theatrical IDM”. 

One potential “drawback” to Suno’s prompting is their rather strict policy on swear words used within a certain context. User’s often say that art is meant to be thought provoking and push boundaries, which can be prohibited by this censorship. 

Udio: Udio also performs well in prompt accuracy, producing music that faithfully follows user inputs. While it tends to adhere to more conventional musical structures, Udio’s precise handling of prompts ensures high-quality and coherent outputs that match the user’s specifications. However controversial, users also have the ability to type in a musical artist that they would like the generation to mimic. To avoid any copyright issues, Udio will then replace the artist name with the closest musical styles within the prompt. 

Features

Suno: Suno offers a range of features, including the ability to extend song clips, blend genres, and generate music with specified moods and emotions. It supports various instruments and styles, providing extensive customization options. Suno’s recent update introduced an audio upload feature, enhancing its versatility and customization. 

Udio: Udio’s features focus on high-fidelity audio generation, extended song lengths (up to 15 minutes), and a straightforward user interface. It allows for detailed customization of song elements and supports a wide range of musical styles. The platform’s ability to maintain high audio quality across different genres is a standout feature, and as mentioned, the user controls it offers such as inpainting or editable song structure provide a hyper creative environment to craft something unique. 

Cultural Impact

Suno: Suno has made significant inroads in the music industry, with artists like Obscurest Vinyl using the platform to create unique tracks that have gained traction on social media and most impressively, Spotify. This highlights Suno’s potential in helping artists break into the music industry without necessarily having technical know-how or traditional musical skills. All you need is an idea, a vision and passion. In this case, Obscurest Vinyl is taking a comedic approach to creating catchy, compelling songs. 

L-R: Will Hatcher, BBL Drizzy AI cover art

Udio: Udio has been leveraged by creators such as King Willonius, a comedian and digital creator who used the platform to create the track “BBL Drizzy.” After seeing a tweet that said the aforementioned phrase, King Willonius simply prompted Udio with a musical style along with the custom text “BBL Drizzy”, and a star was born. 

Metro Boomin sampled the recording (which King Willonius later got credited for), and later Drake himself used the audio in his song “U My Everything”. This caused quite the stir in the music industry, and set a new precedent for what sampling AI generated music means in a professional context.

Using RipX for Customization and Correction

Though these AI tools are incredibly powerful, they can sometimes lack cohesion or consistency. Moreso, users often mention that these AI generations from Suno or Udio are “97% perfect”, and wish that there was a way to change the few bits and pieces that make it imperfect. With this in mind, our DAW RipX provides a powerful way to enhance the outputs from both Suno and Udio by allowing detailed customization and refinement of audio tracks:

1. Customization: RipX separates the instruments within AI generations, and furthermore allows users to edit individual notes of the separated stems. This means that users can change any “off” notes in a vocal performance, add harmonies, change timbre and edit form with ease. It’s also possible to completely replace an instrument within recordings, ie transforming a guitar part into a saxophone sound. 
2. Improving Audio Quality: RipX can isolate and correct distortions or artifacts in Suno and Udio’s outputs, ensuring higher audio consistency.
3. Extended Compositions: RipX can seamlessly stitch together multiple segments generated by Udio, creating coherent long-form compositions.
4. Genre Experimentation: By deconstructing and remixing stems, users can blend Suno’s creative potential with Udio’s high-fidelity sound, producing innovative and unique music tracks.

Overall, the rapid advancement of AI music technologies is undeniably impressive and, for some, even daunting. We are truly on the brink of a revolutionary era in music creation. The future holds many possibilities: how far will we go, and what will these technologies evolve into over the next year? While the answers are uncertain, one thing remains clear: the intrinsic joy of creating music will always captivate people. 

Despite the instant gratification and excitement AI-generated music offers, it will never replace the human desire to learn, experiment, and be actively involved in the artistic process. The journey of crafting art, with all its challenges and triumphs, is irreplaceable.