I tried using AI to create the background music for a podcast, but I may stick to music libraries for now

When I make audio or video content, one element I always struggle with is music. I don't mean a full theme song or anything, but just some basic intro and outro tunes to ease people into the beginning or end rather than just abruptly beginning to speak. There are lots of good music libraries out there, but with the growth of many AI music tools, I thought it would be fun to see if they were any better than me at composing an appropriate musical motif. To properly test it, I decided to quickly make a 'podcast' using another AI tool I'd been toying with, Google's NotebookLM. The Audio Overviews feature can turn documents, video transcripts, and other information sources into AI-generated podcast-style recordings between two AI hosts. On a whim, I picked glass blowing as a topic just because it interests me. I gave NotebookLM a handful of links and videos about the history of glassblowing and how it works. Soon, two AI voices discussed it for more than 20 minutes. But for this, I only needed about ten seconds. I tried a few different AI music tools, including Soundverse, Beatoven, and Loudly. They all had their moments, but most just didn't quite crack it. I tried short prompts, longer detailed ones, and even just keywords. Mostly, they were okay, but often, they were discordant or simply uncomfortable to listen to. After way too long trying out different prompts and edits, I landed on asking Suno to make an instrumental track that would work as the introduction to a podcast about glassblowing- as simple as that. Suno produced two tracks with the evocative title "Shaping Fire and Sand." One was just alright, but the other had the perfect kind of ambient and light classical tone I could easily imagine being heard ahead of a nerdy discussion of annealing and sand purity. When I stitched everything together, it kind of worked - or at least it wasn't distracting from the incoming speech. I ran it by a few friends, and none of them noticed the music being AI-generated, though they did spot the actual podcast as AI voices. You can hear how it went below. I won't pretend it was perfect. I had to set the fading manually, and if the music were from human musicians, you might think they were more enthusiastic than talented. Still, Suno did a great job for a free tool without any complex production required. I don't think I would automatically choose it over something from a human composer, even in a free song library. The customization available with AI can't override human creativity in most cases; the AI podcast proves that. But, as an experiment, Suno made a harmonious addition.

TechRadar

Fri, 4 Apr, 4:00 AM UTC

Music AI Sandbox, now with new features and broader access

Musicians today are drawing inspiration and crafting their sound using a broad ecosystem of tools -- from mobile apps to traditional Digital Audio Workstations, specialized plug-ins and hardware. Now, artificial intelligence (AI) is emerging as a powerful new part of this creative toolkit, opening doors to novel workflows and sonic possibilities. Google has long collaborated with musicians, producers, and artists in the research and development of music AI tools. Ever since launching the Magenta project, in 2016, we've been exploring how AI can enhance creativity -- sparking inspiration, facilitating exploration and enabling new forms of expression, always hand-in-hand with the music community. Our ongoing collaborations led to the creation of Music AI Sandbox, in 2023, which we've shared with musicians, producers and songwriters through YouTube's Music AI Incubator. Building upon the work we've done to date, today, we're introducing new features and improvements to Music AI Sandbox, including Lyria 2, our latest music generation model. We're giving more musicians, producers and songwriters in the U.S. access to experiment with these tools, and are gathering feedback to inform their development. We're excited to see what this growing community creates with Music AI Sandbox and encourage interested musicians, songwriters, and producers to sign up here.

Google DeepMind

Fri, 25 Apr, 6:04 AM UTC

Google has tuned up its AI Music Sandbox for musicians and producers

The Sandbox now includes the Lyria 2 model and RealTime features to generate, extend, and edit music Google DeepMind has brought some new and improved sounds to its Music AI Sandbox, which, despite sand being notoriously bad for musical instruments, is where Google hosts experimental tools for laying down tracks with the aid of AI models. The Sandbox now offers the new Lyria 2 AI model and the Lyria RealTime AI musical production tools. Google has pitched the Music AI Sandbox as a way to spark ideas, generate soundscapes, and maybe help you finally finish that half-written verse you've been avoiding looking at all year. The Sandbox is aimed mainly at professional musical artists and producers, and access has been pretty restricted since its 2023 debut. But, Google is now opening up the platform to many more people in music production, including those looking to create soundtracks for films and games. The new Lyria 2 AI music model is the rhythm section underlying the new Sandbox. The model is trained to produce high-fidelity audio outputs, with detailed and intricate compositions across any genre, from shoegaze to synthpop to whatever weird lo-fi banjo-core hybrid you're cooking up in your bedroom studio. The Lyria RealTime feature puts the AI's creation in a virtual studio that you can jam with. You can sit at your keyboard, and Lyria RealTime will help you mix ambient house beats with classic funk, performing and tweaking its sound on the fly. The Sandbox offers three main tools for producing the tunes. Create, seen above, lets you describe the kind of sound you're aiming for in words. Then the AI whips up music samples you can use as jumping-off points. If you've already got a rough idea down but can't figure out what happens after the second chorus, you can upload what you have and let the Extend feature come up with ways to continue the piece in the same style. The third feature is called Edit, which, as the name suggests, remakes the music in a new style. You can ask for your tune to be reimagined in a different mood or genre, either by messing with the digital control board or through text prompts. For instance, you could ask for something as basic as "Turn this into a ballad," or something more complex like, "Make this sadder but still danceable," or see how weird you can get by asking the AI to "Score this EDM drop like it's all just an oboe section." You can hear an example below created by Isabella Kensington. Everything generated by Lyria 2 and RealTime is watermarked using Google's SynthID technology. That means the AI-generated tracks can be identified even if someone tries to pass them off as the next lost Frank Ocean demo. It's a smart move in an industry that's already gearing up for heated debates about what counts as "real" music and what doesn't. These philosophical questions also decide the destination of a lot of money, so it's more than just abstract discussions about how to define creativity at stake. But, as with AI tools for producing text, images, and video, this isn't the death knell of traditional songwriting. Nor is it a magic source of the next chart-topping hit. AI could make a half-baked hum fall flat if poorly used. Happily, plenty of musical talents understand what AI can do, and what it can't, as Sidecar Tommy demonstrates below.

TechRadar

Mon, 28 Apr, 10:15 PM UTC

Create Original Songs for Free in Minutes with Riffusion AI Music Creator

What if you could compose an original song in minutes -- without ever picking up an instrument or knowing a single note of music theory? Enter Riffusion, a new platform that uses the power of artificial intelligence to redefine how we create and interact with music. Whether you're a seasoned producer looking to push creative boundaries or a curious hobbyist eager to experiment with sound, Riffusion offers a unique blend of accessibility and innovation. With its free AI music generation tools, this platform invites anyone to explore the intersection of technology and artistry, making music creation more inclusive than ever before. In this exploration, Olivio Sarikas uncovers how Riffusion transforms the music-making process through its intuitive design, advanced AI models, and flexible features. From generating custom tracks with simple prompts to remixing and editing existing audio, the platform opens up a world of possibilities for creators at all levels. You'll discover how its free tier provides unlimited relaxed-mode song generation, making it an ideal playground for experimentation, while its paid plans unlock tools tailored for professionals. Whether you're crafting a DJ set, prototyping a new idea, or simply curious about what AI can do for music, Riffusion offers a fresh perspective on creativity that's hard to ignore. Riffusion distinguishes itself through its unique blend of accessibility and functionality. It caters to a diverse audience by offering both a free tier and paid plans, making sure that users of all skill levels can benefit from its features. The platform's free tier allows unlimited relaxed-mode song generations, making it an excellent entry point for beginners or hobbyists. For those seeking more advanced tools, the paid plans unlock additional capabilities designed to enhance the creative process. This tiered approach ensures that Riffusion remains accessible while also catering to the needs of professionals who require more robust features. Riffusion's music generation process is both powerful and flexible, allowing users to create tracks that align with their artistic vision. By inputting detailed prompts, you can guide the AI to produce songs tailored to your preferences. The platform supports the creation of both instrumental and lyrical tracks, offering a wide range of possibilities for experimentation. Additionally, Riffusion allows you to upload audio files for remixing. This feature is particularly valuable for DJs and producers who want to reimagine existing tracks or incorporate unique elements into their music. By combining AI-generated content with your own material, you can create truly original compositions. Here are additional guides from our expansive article library that you may find useful on AI music generation. Riffusion offers a comprehensive set of editing tools that enable you to refine and perfect your creations. These tools are designed to give you full control over your music, making sure that the final product aligns with your artistic goals. These features make Riffusion an invaluable tool for iterative creation, allowing you to experiment and refine your work until it meets your standards. Whether you are crafting a new track from scratch or enhancing an existing one, Riffusion's editing capabilities provide the flexibility you need. Once your music is complete, Riffusion offers multiple export options to suit your needs. You can choose from formats such as MP3, M4A, and WAV, making sure compatibility with various platforms and devices. For advanced users, the platform includes a stems feature, which separates individual instrument tracks. This functionality is particularly useful for: Customization is another key strength of Riffusion. The platform allows you to experiment with different genres, blend musical styles, and personalize lyrics, allowing you to create music that reflects your unique artistic identity. Whether you are exploring new sounds or refining your signature style, Riffusion provides the tools to bring your vision to life. Riffusion is designed to cater to a broad spectrum of users, making it a versatile tool for various creative needs. Its features are tailored to support the following groups: Whether you are a professional looking to streamline your workflow or a hobbyist eager to explore the potential of AI in music, Riffusion serves as a creative partner that adapts to your needs. Its blend of accessibility and advanced features ensures that users at all levels can benefit from its capabilities. Riffusion bridges the gap between technology and artistry, offering a comprehensive platform for music generation, editing, and remixing. Its free tier provides an accessible entry point for beginners, while the paid plans deliver advanced tools for professionals seeking to elevate their craft. With its intuitive interface and AI-driven features, Riffusion enables you to transform your musical ideas into reality, regardless of your level of expertise. Whether you are exploring new genres, fine-tuning a track, or remixing existing material, Riffusion offers the tools and flexibility to support your creative journey.

Geeky Gadgets

Sun, 4 May, 4:12 PM UTC

A Guide to the Best AI Music Tools for Amateur Musicians - Decrypt

Amateur musicians now have a digital band of AI assistants ready to help at every stage of music creation -- from inspiration to final mastering. Whether you're struggling with writer's block, can't quite nail that perfect melody, or just want to experiment with new sounds, there's an AI tool that fits your needs. In fact, there's an overwhelming amount of tools for musicians and would-be musicians. After reviewing dozens of AI music tools from our recent research, here are the best options for each stage of the song creation process. Sometimes all you need is some inspiration to start your creative journey. These tools will help you find new ideas, moods, tones, and even brand new references that might help you conceptualize your musical masterpiece. Suno What it does: Suno is the go-to source for generating songs from simple text prompts. With just a few words describing what you want, this tool creates fully-realized songs, complete with vocals. Paid plans unlock longer tracks, new models that generate more coherent songs with higher-quality audio, as well as tools that will automatically make your song longer. The premium tier also offers the ability to more precisely edit your track and change its lyrics, and provides commercial protection for your masterpiece. Who it's for: Songwriters looking for instant inspiration, people who want to quickly create a full song from a concept, and musicians experimenting with AI-generated tracks as starting point. It's for people who want to create something nice and quick -- without much effort. What it does: Created by ex-Google DeepMind researchers, Udio helps you convert text descriptions into high-quality tracks. It's similar to Suno, but offers more advanced controls -- such as "prompt strength," which lets you control how creative the model is; a "clarity slider", which is basically a resonance suppressor, to reduce unwanted background noise; a negative prompt to avoid specific styles or elements in your generation; and a few other goodies. Udio tends to produce consistently good quality outputs on specific genres like classical or jazz without risking too much in the way of hallucinations. Yes, AI music generators can hallucinate by creating random sounds or lyrics that make no sense. Here's an example of a hallucination produced by Suno, for instance: Who it's for: Musicians who want more control over AI-generated tracks, genre-specific creators (especially classical or jazz), people looking for higher-quality alternatives to Suno. What it does: This tool also helps with inspiration, but it takes a different approach, using AI to generate music riffs based on genres, lyrics, or even emojis. It works like a music-making app on your phone and begins with musical "ideas," not full songs. You start with simple riffs and small bits of songs, or lyrics. You can also check on other users' songs; the mix-and-match approach lets you combine different AI-generated elements, offering more creative control than Suno's all-at-once method. Who it's for: Beginners who might feel overwhelmed by more complex tools, musicians who want to be the ones making the song instead of giving AI full control, and collaborative creators who want to see what others are doing. Price: $99 annually. Snappy lyrics can make or break a song, and AI tools can help you find the right words. Claude and ChatGPT What it does: For those who prefer familiar tools, I think Claude is the best AI chatbot for creative writing. Its lyrics are less robotic, and can be more meaningful and interesting. You can interact with it just as if you were co-writing a song with your pal. Talk in conversational language and it will understand. But ChatGPT has its own style, and is very customizable with the GPT options and its custom instructions. You can configure your own GPT and it will fulfill a similar function as a Claude Project, heavily changing the output Who it's for: Songwriters looking for more natural, meaningful lyrics, those who prefer a conversational approach to lyric writing using AI in an interactive way, musicians who want a co-writing partner. What it does: Offers real-time suggestions and customization options. As you write, it offers alternatives and rhymes that fit your chosen genre and mood. Designed to work alongside you, helping refine your ideas rather than replacing them entirely. It's designed to suggest ideas. You can start writing something and it will analyze the metric, style and mood of your song, and give you inspiration during your process with suggestions for Starts verses, rhymes, ending phrases, etc. It even gives you chord suggestions. Who it's for: Songwriters who want assistance rather than full automation, lyricists looking for suggestions to overcome writer's block, musicians who need help with both lyrics and chord structures. Price: $3.99 to $9.99 per month (Note to internet/AI history buffs: These Lyrics Do Not Exist and Jarvis Lyrics are relics of the good old days. Don't take these too seriously, given the other options, but pour one out for when they revolutionized the internet.) With your idea for a song and with lyrics in hand, the next step is creating melodic lines to bring your words to life. Here are some tools that can help you in this process. MelodyStudio What it does: Specializes in generating tunes from lyrics, supporting genres from rock to gospel. The melodies are royalty-free, and you retain full copyright. The interface allows for editing and refinement. If you suck at music theory and want to put a chord that doesn't fit the structure, this tool will let you know. This tool will give you a good MIDI base that will fit your style, chord progression, and lyrics. You can even use its outputs as inputs for other platforms that are compatible with MIDI, creating a personalized workflow. Who it's for: Songwriters with lyrics but no melody, musicians struggling with music theory, creators looking for MIDI files they can further customize. What it does: AIVA is an OG in the field of AI music production, being around since 2019. It approaches composition from a different angle, letting you select mood and instruments to create original tracks. It's been featured in TED Talks and offers a free tier for non-commercial use. The tool is particularly useful for instrumental sections, creating emotional soundtracks that can complement vocal parts generated elsewhere. Who it's for: Composers looking for instrumental tracks, film scorers, musicians needing background music for vocals, creators seeking mood-based compositions, early adopters who are already used to the tool. What it does: Offers more flexibility for musicians who already know their way around music software. Beyond just generating MIDI, it can extend your musical ideas, suggest variations, or change the mood of existing compositions. Staccato's strength lies in working with your input rather than creating from scratch -- a true collaboration between human and machine maestro. It also has a song analyzer to let you know if your lyrics actually convey the message you want to send, offering tips on how to improve your song. Who it's for: Musicians who already play instruments, composers looking to extend their ideas, songwriters wanting feedback on their lyrical messaging. What it does: Upload an MP3 of any song and Moises will separate tracks into "stems" (individual instrumentals and vocal parts), letting you isolate what you need. It'll also break down the chords that the song uses, a la Chordify. Beyond just separation, Moises also transcribes melodies, and provides tempo and key control. If you went the Suno route and generated a full song -- or if you have a full song and want to isolate a single instrument, or create a backing track out of it -- this tool will do the job and will be very helpful if you plan to play that song live with your band. Who it's for: Musicians practicing with existing songs, remixers, bands wanting to learn or perform AI-generated tracks, people looking to isolate specific parts of songs. What it does: Performs similar functions to Moises with a simpler interface, separating vocals and instrumentals with a single click. While it lacks some of Moises' precision, it's a no-cost, open-source option for basic separation needs. Who it's for: Budget-conscious musicians, casual users needing simple track separation, open-source enthusiasts. Link: StemRoller or https://github.com/stemrollerapp/stemroller/ Price: Free. The app is open source, so the code has been reviewed by thousands of independent developers and is auditable, so it's apparently safe to download and install. If you're worried, download it from the Github site. BandLab Studio What it does: Offers a full-featured online DAW with integrated AI tools. What makes it stand out is its community features -- you can collaborate with other musicians remotely, access sound libraries, and use AI to extend your compositions. Its SongStarter feature generates track ideas from simple prompts like genres or emojis, giving you a foundation to build upon. It's a great middle ground between fully AI-powered platforms like Suno and time-proven music editors like FL Studio. Who it's for: Collaborative musicians, producers wanting a free DAW with AI features, beginners learning production skills, social music creators. Price: Starts at $99 per year Arrangement turns basic compositions into fully realized songs by determining how different elements work together. If this is what you need, check out some of these tools. RecordLabel What it does: Brings unique capabilities to the arrangement process, allowing you to transform vocal recordings into instruments for creative arrangements. It also features a wide set of tools that leverage AI to one-click your way through the music production stage. RecordLabel will improve your recordings with little effort, making them brighter, bassier, cleaner, and overall better in quality, based on your needs. Who it's for: Producers looking to transform vocal recordings, musicians wanting quick production enhancement, creators seeking creative arrangement tools, people who need editing but lack the expertise. What it does: A good tool for producers experimenting with instrumentation, such as turning a hummed melody into a guitar riff or orchestral string section. It offers a complete suite of tools that will make your creative process more enjoyable. It can help you clone voices, split songs into stems to practice each instrument, find the key and BPM of any reference, use AI to master your demos and much more. Who it's for: Experimental producers, musicians wanting to transform melodies between instruments, technical creators who can navigate complex UIs. Premium: Starts at $9.59 The final step -- making your song sound professional -- has traditionally required expensive studio time. These are some AI tools that are trying to change that equation. Landr What it does: Offers an end-to-end solution for mastering. This one is huge and provides a lot of tools for musicians and AI enthusiasts -- from a complete AI mastering suite to a social media platform that lets you connect with other creators and sell your products. The AI mastering engine claims to have been trained by Grammy-winning producers and offers unlimited revisions. Beyond mastering, it includes distribution to over 150 streaming platforms and access to millions of royalty-free samples. Who it's for: Independent musicians seeking professional mastering, creators wanting distribution options, producers looking for royalty-free samples, musicians eager to learn through the platform's courses. What it does: This program provides more granular control for those comfortable with audio engineering concepts. Its AI-powered features include vocal balance assistance and stem focus, allowing precise adjustments to specific elements of your mix. This one is not really the best option for amateurs that want to make songs for fun, but is worth mentioning because it's a very complete tool. Who it's for: Advanced audio engineers, professional producers, technical musicians with audio engineering knowledge.

Decrypt

Sat, 17 May, 6:04 PM UTC

Riffusion

Free

About Riffusion

Related fields

Related News

Similar products

AI Music Generator

Aiva

Mubert

Suno AI

HookGen