Experimenting with AI music generation

Experimenting with AI music generation

Suno is a generative AI tool for creating music. I’ve been experimenting with it for generating music clips. It’s fun!

At first I thought pretty much all the Suno clips sounded the same (similar pop music styles). But I’ve been experimenting and I’ve come to like it! You really can generate many different styles of music.

 

My musical background

My first career was as a classical musician (I played pipe organ and harpsichord). I have a Masters in Music from Boston Conservatory and I spend my twenties working as a performing musician in Boston. That meant playing for weddings, funerals, freelancing in different orchestras, and teaching lessons.

I became a music librarian in order to support myself as a performing musician. My first job out of library school was as the music librarian at the Longy School of Music, in Cambridge, MA.

By the time I turned thirty, I decide that performing was too stressful, and I enjoyed my library work more. So I transitioned to working as a full time librarian. I’ve worked as a general reference librarian (Emmanuel College, Boston), a systems librarian (Bose Corporation), a library web manager & head of UX (MIT Libraries), and now I’m an elearning developer (University of Arizona Libraries).

Since I’m very interested in testing new AI tools, and also have a music background, Suno piqued my curiosity!

 

How does Suno work?

Enter a text prompt and it will create a short clip of music based on that prompt. You can then extend your clip to make a longer version.

You can generate music with or without vocals. It uses ChatGPT to create lyrics for you, or you can write your own lyrics. Free and paid accounts are available. You can create about 10 songs per day with the free version.

  • If you are using a free version of Suno, they retain ownership of the songs you generate, but you’re allowed to use those songs for non-commercial purposes.
  •  If you are a paying subscriber to Suno, then you own the songs you generate. (I’m a paying subscriber).

Learn more in their FAQs.

 

So what do I think of AI music generation?

I think it’s great fun! I actually like some of the clips I’ve generated.

I’ve generated many different genres, not just the various popular styles you usually hear from them.

Like all generative AI tools you need to keep experimenting with different prompts and you won’t like every output. And be sure to use “custom mode” if you don’t want it to rewrite your prompt. A good place to get ideas for musical styles and terms is in this Wikipedia article: List of music genres and styles.

Here are some clips I’ve generated — just to see various styles I could get it to output.

Jazz piano

Bebop

Light orchestral

Klezmer music

Afro-pop female vocal
(ChatGPT made the lyrics, and then I used ChatGPT to translate it to French)

Hypnotic, electronic, synth-pop, krautrock

Bluegrass fiddle band

Circus clown

 

How well does it do with classical music?

Even thought the technology is pretty good for many types of music, it does get a bit weird when asked for specific styles of classical music.

For example, when asked for impressionist piano music (in the style of Debussy or Ravel), it often creates something that sounds more like Mozart. And for other genres and periods it often generates the basic sounds and structure pretty well, but the harmonies are weird. I would guess that it either lacks the training data, or I just haven’t found the best words to prompt it with.

Here are a couple of clips that came out ok, though. They aren’t masterpieces, but they could work for background music when you want certain kinds of atmosphere.

Renaissance boy choir (I gave it the lyrics to Gloria in Excelsis Deo)

Baroque pipe organ

 

What does this mean for professional musicians?

I really don’t think people will ever stop learning to play instruments, attending live concerts, or making music for fun. What technology like this might be used for is creating clips to use for YouTube videos, advertisements, and other types of background music. It could compete with various royalty free music collections that are used for background music everywhere.

Also, AI music generators make it easier for people to create music even if they lack formal musical training or access to expensive equipment and lessons. This opens up musical expression to a wider range of people.

I agree with Carlos Arana of Berkeley Online who discusses this in more detail in What is Generative AI and Should Musicians be Afraid? 

By the way, here’s someone who has made an AI version of her own voice. She’s got some interesting ideas about all of this. See AI is changing music forever,  Holly Herndon and Mat Dryhurst.

Siri, Alexa, and Other Digital Assistants: The Librarian’s Quick Guide

Siri, Alexa, and Other Digital Assistants: The Librarian’s Quick Guide

I’m working on a new short book, to published by Libraries Unlimited later this year.

Siri, Alexa, and Other Digital Assistants: The Librarian’s Quick Guide

Here’s the draft table of contents.

1. What is Voice-First Computing?

  • Introduction
  • Why It’s Important for Librarians to Be Familiar with This Topic
  • Definitions
  • Platforms Overview (Alexa, Google Assistant, Siri, Cortana)
  • Typical Tasks
  • Statistics
  • History of Voice Computing
  • Advantages of Voice Computing
  • Speech Recognition and Natural Language Processing

2. Hardware and Skills

  • Hardware
    • Smart Speakers (Amazon Echo devices, Google Home Devices, Apple’s HomePod, Microsoft’s Cortana on the Harmon Kardon Invoke)
    • Smart Home Devices
    • TV Devices
    • Smart Toys & Robots
    • Voice Computing in Cars
  • Comparing Platforms
  • Third-Party Skills
  • Creating Skills
  • Using Automation to Connect Tasks with Other Apps

3. Real-World Uses

  • Hands-Free Situations
  • Workplace Uses
  • Benefits for the Elderly
  • Benefits for People with Disabilities
  • Ideas for Uses in Libraries
  • Design Issues for Voice Interfaces

4. Privacy and Ethical Concerns

  • Uses of Voice Data in Ways You Didn’t Intend
  • How to Turn Off Microphones and Delete Recordings
  • Privacy Recommendations for Design of Voice Assistants
  • Sexism in Voice Computing
  • Children and Voice Assistants
  • What Librarians Need to Know

5. The Future of Voice Computing

  • A Primary Way of Using Computers
  • Voice Everywhere
  • Hearables & Smart Glasses
  • Moving from a Mobile-First to an AI-First World
  • Possible Future Uses in Libraries

Appendix

  • Bibliography
  • Index

This is a fun and interesting topic to write about! It’s a rapidly changing technology, so I’m publishing this on a quick timeline. If you have ideas for what else you would like to see discussed in the book, let me know!

Podcasts for diverse audiences

Podcasts for diverse audiences

Are there many podcasts by and for people other than white male techno-geeks?

That’s something I looked into when writing the report, “Podcast literacy: recommending the best educational, diverse, and accessible podcasts for library users” (coming in 2017 from ALA TechSource).

Maybe not…

According to Pew Research, “They’re more likely to be male, young, have higher incomes, be college graduates, live in an urban area.” (“Podcast’s biggest problem isn’t discovery, it’s diversity,” Wired, Aug. 31, 2015).

But wait…

But as of late 2016, there is some good news. Edison Research, a group that has been tracking demographics of podcast listeners for over a decade says, “…In the early days of the medium, podcasting was disproportionally a medium for white males, ages 25-44. … but today, the content universe for podcasts has exploded, and the diversity of programming available rivals any other form of audio.”

So how do you find podcasts for diverse audiences?

One place to look is the site of a podcast collective called Postloudness. Based in Chicago, it’s aiming to create a community of shows by women, people of color, and queer-identified hosts. Their goal is to bring more diversity to podcasting and help underrepresented voices create their own shows.

Get my report

Postloudness is a good place to start, but there are many more diverse podcasts available. In order to assist librarians with recommending podcasts for diverse audiences, I’ve complied lists in the following categories:

◆ produced or hosted by women
◆ racial and ethnic diversity (African-Americans, Latinos, Asian-Americans, Native Americans)
◆ LGBTQ (lesbian, gay, bisexual, transgender, queer or questioning)
◆ aging and ageism (elders’ & children’s rights)
◆ homelessness, poverty and economic class
◆ people who are (or were) incarcerated
◆ adult literacy
◆ neurodiversity and mental health issues
◆ physical disabilities

To get this annotated list of podcasts for diverse audiences, watch for my report from ALA Tech Source, available in 2017.

Learn more about what this report covers:
Podcast Literacy – table of contents


To be notified when the full report is available, sign up for my newsletter.

Mobile Apps News: stay current with mobile apps