To speed up and simplify music production, many artists now employ artificial intelligence to create AI-generated music. In the past few years, AI has matured as a compositional tool, allowing musicians to discover new sounds derived from AI algorithms and software. As a result, AI-generated music has become mainstream and is adding another dimension to the music industry.
AI Music Generators and Tools to Know
- Soundraw
- Aiva Technologies
- Beatoven.ai
- Soundful
- Suno
- Udio
How Does AI-Generated Music Work?
AI-generated music works when you feed large amounts of data to AI algorithms that study chords, tracks and other data to determine patterns for creating music similar to the information the algorithms have processed.
Artists have started to embrace this technology and its capabilities, leading to an increasing demand for AI music generators.
11 AI Music Generators and Tools
While advanced compositional AI remains the most interesting AI-in-music endgame for many, AI has already been impacting the music industry for years. AI-generated mindfulness ambient music, rights-free music generation for content creators and automation-assisted mixing and mastering have all matured into major industries.
Here’s a closer look at some notable players.
Soundraw
Soundraw is a royalty-free music platform that uses AI to tailor songs to the needs of creators. Selecting and molding factors like mood, genre, song length and chorus positioning, creatives can develop personalized musical tracks that align with video sequences. Soundraw users also avoid some of the copyright issues that arise on other platforms, making it even easier to create and distribute music.
- Notable features: Royalty-free music, options for customizing songs to fit video sequences
- Cost: Plans start at $16.99 per month
Aiva Technologies
Aiva Technologies is the creator of a soundtrack-producing artificial intelligence music engine. The platform enables composers and creators to make originals or upload their work to create new variations. Depending on the plan chosen, creators can also forgo the worry of licensing because the platform offers full usage rights. Rather than replacing musicians, Aiva wants to enhance the collaboration between artificial and organic creativity.
- Notable features: Ability to quickly produce variations of a musical work, full usage rights
- Cost: Free plan with additional plan options
Beatoven.ai
Beatoven.ai allows creatives to develop customized background music using text prompts. Users can fine-tune prompts to edit the genre, instrumentals and emotional elements of a track. When users download tracks, they also receive licenses via email to maintain full ownership over their content. Beatoven.ai claims to be a “fairly trained certified AI provider” and compensates musicians who let the company use their music to train its AI models.
- Notable features: Prompt editing for personalized music, licenses emailed after each download
- Cost: Subscription plans start at $6 per month with additional plan options
Soundful
Soundful is an AI music generator that produces background music for social media, video games, digital ads and other formats. Users choose from a broad range of music templates and moods, adapting tracks to their specific needs. Larger organizations can select Soundful’s enterprise plan to establish licensing terms and ways for monetizing templates, ensuring their creative endeavors remain profitable.
- Notable features: Royalty-free music, broad selection of moods and templates, licensing and monetization plans available
- Cost: Free plan, with option to upgrade to premium, pro or a business tier plan
Suno
Suno is based in Cambridge, Massachusetts, and features a team of musicians and AI experts who hail from companies like Meta and TikTok. The AI tool has made a habit out of generating songs that have gone viral, thanks to its ability to produce instrumentals, vocals and lyrics from a single text prompt. Users can play around with prompts to craft a song about a particular topic and in a specific genre.
- Notable features: Instrumentals and vocals generated, ability to edit genre and topic
- Cost: Free plan with additional plan options
Udio
Developed by former Google Deepmind researchers, Udio is an AI generator that lets users create unique tracks with prompts and tags. After writing a prompt, a user can make further tweaks by adding tags that alter elements like the genre and emotional tone of the song. For each submission, Udio produces two versions and features a prompt box that doesn’t reset, so users can continue to adjust and build on previous prompts.
- Notable features: Tags to edit specific song elements, a prompt box that doesn’t reset
- Cost: Free plan with additional plan options
Meta’s AudioCraft
With the release of its text-to-audio tool AudioCraft, Meta is taking generative AI in music to another level. AudioCraft is trained on licensed music and public sound effects, so users can quickly add tunes or sounds to a video with text prompts. Leveraging a neural network model called EnCodec, AudioCraft delivers high-quality sounds on a consistent basis and compresses files for faster sharing.
- Notable features: Trained on licensed music and public sound effects, text-to-audio abilities
- Cost: Free
iZotope’s AI Assistants
iZotope emerged as a pioneer in AI-assisted music production back in 2016, with the release of Track Assistant. The mixing feature uses AI to generate custom effects settings based on the sonic palette of a given track. Today, it hosts a full suite of assistants that tailor starting-point suggestions for vocal mixes, reverb application and mastering.
- Notable features: Collection of AI music assistants
- Cost: Products range from $29 to $2,499
Brain.fm
Brain.fm is a web and mobile application that provides atmospheric music to encourage rest, relaxation and focus. Created by a team of engineers, entrepreneurs, musicians and scientists, the company’s music engine uses AI to arrange musical compositions and add acoustic features that enable listeners to enter certain mental states. In a pilot study led by a Brain.fm academic collaborator, the application showed higher rates of sustained attention and less mind-wandering, which led to a boost in productivity.
- Notable features: Music that caters to certain mental states, product backed by neuroscience and psychology research
- Cost: $9.99 per month or $69.99 per year
LANDR
LANDR is a creative platform that enables musicians to create, master and sell their music. The company’s mastering software uses AI and machine learning to analyze track styles and enhance parameters based on its reference library of genres and styles. Beyond AI-enhanced mastering, LANDR enables musicians to create quality music and distribute it on major streaming platforms while avoiding the costs associated with a professional studio.
- Notable features: Library of music samples, independent music distribution
- Cost: All-in-one subscription for $13.74 per month, with additional plan options
Output’s Arcade Software and Kit Generator
Output’s signature software Arcade lets users build and manipulate loops into full-length tracks. Users can access audio-preset plug-ins, then adjust sonic details like delay, chorus, echo and fidelity before minting a track. The software also features an AI-powered tool called Kit Generator, which lets users generate a full kit, or collection of sounds, from discrete audio samples. Output’s technology has supported music by artists like Drake and Rihanna and the scores of Black Panther and Game of Thrones.
- Notable features: Track-building software, AI tool for creating collections of sounds
- Cost: Free trial available for a limited time, prices may change
Impact of AI on Music
Much remains to be seen about how musicians and companies respond to the spread of AI. But one thing all parties can agree on is that AI-generated music has forever changed the industry — in both promising and problematic ways.
Leads to New and Different Forms
The rise of AI-generated music has led to companies and individuals offering unique takes on renowned songs and artists.
For example, the piece “Drowned in the Sun” is the product of Google’s Magenta and a neural network inputting data from dozens of original Nirvana recordings and crafting lyrics for the singer of a Nirvana tribute band to perform. Although the audio is a bit muddy, AI has impressed even those in academia with its abilities.
“It’s able to coherently generate a multi-instrumental piece of music with metrical structure, musical phrases, progressions that make sense, all while doing it at a granular audio rate,” said Oliver Bown, author of Beyond the Creative Species.
Offers Artists More Creative Options
Writer Robin Sloan and musician Jesse Solomon Clark created an album using OpenAI’s Jukebox, which, like Magenta, can predictively continue a musical snippet. Holly Herndon’s 2019 album, Proto, described by Vulture as the “world’s first mainstream album made with AI,” incorporated a neural network that generated audio variations based on hours of vocal samples.
“[Herndon is] working with AI as this sort of extended choir,” Bown said.
Inspired by these applications, artists and technologists hope for an even greater step forward. One possibility for AI in music could be models that respond to artists in real-time performances. Rather than edit down the interesting bits offered by a model, humans could bounce off musical ideas with AI, just like a bass player and drummer in a rhythm section.
“It’s a long shot, but it could have a huge impact,” said Roger Dannenberg, a professor of computer science, art and music at Carnegie Mellon University.
Hinders Originality
AI has been able to replicate the sonic qualities of artists, but the innovation that defined famous musicians has remained elusive. The effect of AI producing songs that sound similar to previous works is a lack of variety and quality in AI-generated music pieces.
“Nirvana was famous for doing things in a different way than had come before,” said Jason Palamara, assistant professor of music and arts technology at Indiana University-Purdue University Indianapolis. “But machine learning is really good at doing things the way that humans have already done them before.”
Hope persists for a not-too-distant future where AI moves beyond mimicry and riffs with human musicians, but rudimentary versions of this technology are flawed by a lack of sophisticated real-time musical interfaces. This means simple details for humans (like synchronizing and beat tracking) are a major challenge for models, Dannenberg said.
The data limitations are pronounced, too. The “Drowned in the Sun” Nirvana track stems from hours of rich MIDI data, but a live performance generates scant audio in comparison. So, for live-music generation, “you have to kind of dumb it down,” Palamara said.
Sparks Copyright Conflicts
Similar to the arenas of AI writing and AI-generated art, the legal framework for AI in music remains murky. Those who produce AI-generated music may not be able to copyright their music while musicians whose songs were analyzed may not know when it’s appropriate to sue someone for copying their lyrics or any other musical elements too closely.
Debates around the authenticity and accuracy of AI music and who owns what have culminated in a legal battle. A group of record labels has sued companies on the grounds of copyright infringement, putting the future of the entire AI industry in limbo for the time being.
Raises Concerns Over Job Losses
Job losses due to automation are a major worry when it comes to AI, and music is no exception to this trend. AI that produces beats, rhythms and melodies may take over the roles of drummers, bassists and other musicians.
Of course, the ultimate goal is to have artificial intelligence supplement musicians, serving as collaborators for adding fresh sounds and techniques to the creative process. However, AI causing job losses in the music industry is a very real possibility that artists, technologists and other parties need to weigh when relying on AI music generators.
Frequently Asked Questions
Is there an AI that can make music?
There are plenty of AI music generators on the market, with Aiva Technologies, iZotope and OpenAI being just a few companies that build this technology. This field continues to grow, with Meta being the latest company to offer an AI music tool in the form of AudioCraft.
What does AI music do?
AI music can generate new sounds and beats to enhance soundtracks. Artists may also bounce ideas off of AI music generators, feeding them lines and letting these tools continue the lyrics and instrumentals to produce new versions of songs.
How do you make AI music?
Artists train algorithms on musical data, which can be anything from a single chord to an entire soundtrack. AI music generators then churn out music in a style and sound similar to that of the musical information they were fed.
Is AI-generated music legal?
Under current United States copyright law, only a human being can copyright a creative work. As a result, AI-generated music has avoided copyright infringement and is considered legal since the final product technically wasn’t produced by a human. But this could change as major record labels sue AI music startups like Suno and Udio.
