Day 5 – Create Music and Songs – 30 Day AI Challenge 2024

Welcome to the 2024 Edition of the #30DayAIChallenge. This year, we’ll be focusing on making Generative AI more accessible for all. So follow along and give each challenge a try yourself, plus share your own thoughts and experiments with a community of like-minded learners and tinkerers!*

Week 1‘s theme is “Enter The Matrix, Creativity Reloaded“, focused on what you can do personally to tap into your creative spark, plus bring ideas to life.

Today’s Challenge – Making Music, Songs using Generative AI

Today, we go deeper down the creativity rabbit hole to see what GenAI has in store for us. With new generative AI tools, the ability to create music and songs has become more accessible than ever before. This challenge invites you to explore and utilize AI tools to compose your own unique pieces of music. Whether you’re a seasoned musician or someone who has never touched an instrument (like me!), today’s technology opens up endless possibilities for creativity.

For The Newbies Amongst Us

For beginners such as myself, starting with user-friendly platforms like Suno.ai can be an excellent way to get into AI-generated music. Suno.ai offers a straightforward way to create music: simply provide some input in terms of genre, mood, or even a set of lyrics, and the AI does the rest. Here’s how you can start:

1. Explore available AI music generators like Suno.ai, Mubert, and Soundful (to name just a few). These platforms are designed with the novice in mind, offering easy-to-navigate interfaces and straightforward creation processes.
2. Experiment with different inputs. Try altering the genre, tempo, and mood to see how each change affects the final piece of music.
3. Engage with the community. Many of these platforms have forums or social media groups where creators share their works and tips.

Let’s Create A Song:

Let’s give it a quick try…for our challenge today, we want to create a funny song about “A Day in the Life of a Cat from Their Perspective“. For our demonstration we’ll use Suno, which now offers a user-friendly web interface (previously it was only accessible via Discord).

Using the simplest possible approach, you can simply put in what you want, hit create and let Suno do the rest.

In less than a minute, you have a couple of options you can play with, download as audio or video…and even extend. Here’s one of those samples:

You can also get more specific about what you need, using the custom mode:

Here’s one the options Suno produced using the above prompt…

Let’s Create Some Simple Background Music:

You can also use GenAI tools to create supporting audio tracks and background music for videos and other uses…here’s a quick example using a tool like Mubert. The simplest way to do this is just put in a prompt describing what you need, and the tool will create the audio using your text input.

Here’s what Mubert produced:

Similarly you can also create music using Genres, Moods or Activities…or even upload a picture as a prompt. Mubert doesn’t allow the use of this content on streaming services, and when you download created tracks you can also specify which channels you will be using them on so they can clear any copyright claims.

The Advanced Approach

For those with more experience or seeking a deeper dive into AI music creation, consider platforms like Aiva or Audiomodern Playbeat (among others). These tools offer more advanced controls and customization options, allowing for a finer touch on the compositions. Here are some tips for advanced users:

1. Integrate AI music tools into your digital audio workstation (DAW) to blend AI-generated tracks with your own recordings or compositions.
2. Experiment with AI-generated stems and samples, customizing and layering them to create complex arrangements.
3. Dive into the settings of AI music generators to fine-tune parameters like key signatures, chord progressions, and instrument choices.

There are also plenty of creators now experimenting with combining AI generated music with videos to create new art. Here’s an interesting example by Uncanny Harry, where he has used Suno AI, FaceFusion, Lensgo, Leonardo and other tools to create a ‘music video’.

Not amazing, especially by today’s non-AI music video standards…but then again, this is the worst it’s ever going to be, plus this was put together by an enthusiast in just a couple of days. More recent, professional examples include the use of AI by the Beatles and Abba.

The Beatles’ track “Now and Then” features John Lennon’s vocals thanks to advancements in artificial intelligence. In the past, isolating Lennon’s voice from the original 1969 demo proved difficult because it was recorded with a single microphone and included background noise from a television and piano. However, director Peter Jackson, who also worked on the “Get Back” documentary, employed machine learning technology to separate the instruments and vocals.

This technique is similar to what was used for the recent ABBA Voyage concert experience, where digital avatars of the band performed alongside live musicians. In both cases, AI allowed artists to revisit and complete creative projects in a new way.

Key Considerations and What to Watch Out For:

1. Usage Rights and Licensing: Most AI music platforms offer different levels of licensing based on the subscription plan. It’s crucial to understand the rights provided under each plan. For instance, some plans may allow for commercial use, while others are restricted to personal or non-commercial projects. Ensure you choose a plan that aligns with your intended use.
2. Royalty-Free vs. Royalties Required: While many platforms advertise their music as royalty-free, meaning you don’t have to pay ongoing royalties for its use, this does not always exempt you from obtaining the proper license. Always verify the licensing agreement to understand whether you’re getting a royalty-free license or if there are specific conditions attached.
3. Integration into Commercial Projects: If you plan to use AI-generated music in commercial projects, such as video games, films, or advertisements, look closely at the platform’s policies regarding commercial use. Some platforms may require a special licensing agreement or an additional fee for commercial use.
4. Customization and Export Restrictions: Some AI music tools limit how much you can customize the music or restrict the formats in which you can export your creations. These limitations could affect your project, especially if you require high-resolution audio files or specific file formats for compatibility with other software.
5. Quality and Originality: While AI can generate music in a variety of styles and genres, the output might not always meet the quality or originality you’re seeking. Listen to samples and read user reviews to gauge whether an AI music generator can meet your standards.
6. Cost Efficiency: Compared to traditional music production routes, AI-generated music can be more cost-effective, especially for individuals or small businesses with limited budgets. However, costs can vary widely based on the platform, usage rights, and level of customization needed. Evaluate different platforms to find the best value for your needs.

A Note of Caution: AI Song Covers

Imagine this: AI tools can now mimic the voices of famous singers and actors to sing songs or say things. Here’s an example, where someone has used Johnny Cash’s voice and he’s featured in this video singing ‘Barbie Girl’:

These voice models and AI covers now proliferate the internet…they have some entertainment value, but are also tricky because they involves using someone’s voice without asking them first, which can upset some people and break some rules.

Picture a company that helps voice actors make money by letting others use their voices in a fair way (ElevenLabs is a great example). And think about singers like Grimes, who says it’s okay to use her voice for AI songs if she gets paid a fair share. This situation shows how we’re figuring out new ways to handle creative work and pay people in the age of AI. It’s all about finding a balance between making awesome new stuff and respecting everyone’s rights.

Wrap Up

The intersection of AI and music opens up exciting new horizons for creators, offering tools that can inspire, assist, and enhance the creative process. As these technologies evolve, the future of music creation looks bright, promising even more intuitive interfaces and higher-quality outputs. The democratization of music production through AI not only makes it more accessible but also invites a diversity of voices and ideas into the realm of music creation.

Embrace today’s challenge to explore the limitless possibilities of AI in music creation. Whether you craft a chart-topping hit or simply enjoy the process of creation, the experience of making music with AI is sure to be rewarding!

Look forward to hearing about your own experiences…leave a comment and let us know, or tag your Facebook, Twitter / X or LinkedIn post with #30DayAIChallenge so others can find it too.

Till tomorrow…

*Please note: Participation in the 30 Day AI Challenge is at your own discretion and responsibility. Always ensure that no sensitive personal information, confidential, or proprietary company data is shared. Adhere to all applicable local laws and company policies. Enjoy exploring AI responsibly!