top of page
Search

Splash Music: New Text to Song Generator Includes AI Vocals

Splash Music is a brand new AI text-to-song application, featuring a generative music engine with AI vocal overpainting. The company offers web and mobile apps that anyone can use, regardless of their training or music background.



In this article we'll provide a general overview of the app's core features, compare the music output to other AI song generators like Chirp and VoiceMod, and finish with some brief commentary about their Terms of Use.


Table of Contents

  1. How does Splash Music generate AI music?

  2. How do you add AI vocals to songs on Splash?

  3. What do AI songs from Splash sound like?

  4. Best alternatives to Splash Music (Chirp, Voicemod, AudioCipher)

  5. What are Splash Music's terms of use for publishing songs?

How does Splash Music generate AI music?


The text-prompt interface is a core feature at Splash. Users describe music and can quickly generate song cues in that style. A few musical parameters like BPM, key signature, and scales (modes) are available for those who need it.


Text prompt field in Splash Music

Within 20-30 seconds, the system generates four short samples accompanied by AI-generated images. Each sample can be auditioned with playback controls and expanded via the select button. There's a dropdown arrow that can be used to generate similar variations on the reference track. If none of the music feels right, Splash also includes a more unique samples button that creates entirely new music. Here's what that interface looks like:


Splash music dashboard

One of the best features at Splash is the ability to store each new step in your generative process. Prior choices are kept on-page while the system introduces newly generated content. The layout is on par with the workflow of chat apps like ChatGPT and Perplexity. It's a big improvement on the AI music interfaces from Google and Meta.


Generating music in Splash

Once a sample has been selected, Splash will expand into a 15 second clip, as shown above. A new set of options become available. Users can mark their favorite tracks, download and share the audio files and use the Edit Song button to make changes to the duration. Paying subscribers have the option to generate songs that are 30 seconds or longer.


Choosing a song duration

The edit song panel also features a Vocals section. This gives you the option to add lyrics to a song. In the past, most of the AI vocal generators we've seen have run separately from an AI music generator. The AI rappers at Splash are big part of the product's character, differentiating it from text-to-music services like MusicGen, MusicLM, Stable Audio and Riffusion. You can listen to a side-by-side comparison of Splash to these other AI music generators here.


How do you add AI vocals to songs on Splash?


To add vocals to Splash songs, users begin by clicking the add lyrics button. A new text area appears with several options for customization. Users can write their own lyrics into the box or use the prompt magic tool labeled Lyrics to get help from an AI lyric generator.

Splash music lyric interface

After clicking the lyric button, a popover ask for a short prompt that indicates what the song should be about. It can generate simple four line stanzas or create enough content for a full length song. Simply hit the create lyrics button to close the window and populate the text area in your song dashboard.

AI lyric generator

Next, you'll need to select an AI voice that can perform the lyrics. The free version of Splash comes with only one option; an AI rapper named Jacob.


A total of three rappers and ten singers are available on the paid plan. Each vocalist has a different timbre and cadence. Click the play button next to a name to hear what they sound like before committing to the paid plan.

Selecting an AI vocalist

Quick tip: Make sure that each line in your lyrics includes a paragraph break. Otherwise the AI vocalist will speed-sing the songs and try to cram everything into a small portion of the audio sample. If the lyrics don't fit into that space, Splash will exclude the rest of your lyrics. By placing the lines on separate paragraphs, you can hear the lyrics evenly spaced over the whole track.


To hear more than one AI voice on a track, hit the add lyrics button a second time and type up some new lyrics. Click on the AI voice name and select someone else instead. You can repeat this process multiple times until you have all the different sections that you need. Drag and drop the modules up and down the timeline to hear how they sound in different orders.


This Splash workflow gives listeners the feeling of hearing a pop song with "featured artists". When you're ready to proceed, hit the Apply Changes button and moments later you'll have a new version of the track with AI vocals. We found the speed and quality of the output to be great!


Finished AI song example

What do AI songs from Splash sound like?


Splash supports a diverse range of music genres, but their sound design is exclusively electronic. On the one hand, this means that users can enjoy high fidelity audio and music that's snapped to a grid. On the other hand, it also means that Splash won't create anything resembling a live band or orchestra. The music always sounds digital.


Watch the video below to listen to some examples of the kind of music and album art that Splash creates:



Splash may be a new company, but they've already cultivated a vibrant community of music creators. Many of these artists are featured on their YouTube channel. They've partnered with some other interesting companies like the AI Music Video Generator Neural Frames, creating trippy visuals that go will with AI generated music.


An example of the Neural Frames collaboration can be seen below, where lofi beats are coupled with colorful, animated sea creatures:



Best Alternatives to Splash (Chirp, Voicemod, AudioCipher)


In my opinion, the best alternative to Splash is the text-to-song app Chirp by Suno AI. They offer music generation on Discord instead of web and mobile. Chirp is completely free to use at this time and supports unlimited song generation, including similar lyric-to-vocal and album art features found on Splash.


What are the benefits of using Chirp AI vs Splash Music for text-to-song?



The key difference between Chirp and Splash is the audio aesthetic. Chirp generates raw audio, whereas Splash performs MIDI with sound design. As a musician, I like Chirp's music a bit more due to greater range of styles that it can create. Splash is limited to electronic arrangements, making it a good fit for genres like EDM and Trap but not capable of classic styles like rock and jazz.


Splash makes up for these limitations with usability and ease of access. The web and mobile apps are convenient for people who don't already use Discord. They are also more conducive to storing and browsing existing projects. Unlike Chirp, Splash projects don't get buried deep in the Discord chat timelines.


The library dashboard (shown below) include the options to view all of your past generations or highlight only your favorite ones:


Splash music user library

How does Splash Music compare to Voicemod's text-to-song app?


Splash is competing with at least one other web application. VoiceMod's text-to-song app is a 'meme machine', which makes it sound like a silly play thing. But Voicemod's app lets users select from preset genres, choose from different AI vocalists, and enter lyrics to be turned into vocal melodies on the track.



The main difference you'll find with Voicemod is that it's not generating AI music from scratch. As a meme machine, the company's goal is not to create original songs but rather to make funny content that users can share with friends and family. So if that's your goal, the app is free to use and you can scratch the creative itch without paying anything.


Splash isn't necessarily a tool for musicians, but it's closer to a music creation tool than Voicemod. It includes publishing licenses that let users distribute their songs on streaming platforms like YouTube, Spotify, and Apple Music.


Comparing Splash Music to AudioCipher


AudioCipher is another generative text-to-music software company, but it caters to a different crowd. It's a DAW plugin and standalone app that lets users transform words and phrases into melodies or chord progressions.


AudioCipher v3

Both AudioCipher and Voicemod support the option to pick key signatures and control the music's rhythm, but AudioCipher exports in MIDI format instead of mp3 or wav. It's a creativity and inspiration tool for musicians rather than a "finished song" generator. You can watch demo of the app below:



What are Splash Music's Terms of Use for publishing?


A word of warning before we wrap up here: The Splash Terms of Use indicates that music you create with the platform can be published under a royalty-free license.


However, they clearly reserve the right to "limit your use of the Recordings or require you to cease using them (and delete any copies of them) if we form the view that your use of the Recordings would infringe the rights of any third party, including Open AI."


Their terms further indicate that "You grant us a royalty free, irrevocable licence to reproduce, communicate and otherwise use and exploit any Song Prompts or User-Submitted Lyrics submitted by you, to the extent required for us to operate Splash AI."


This means that Splash Music users enjoy a kind of limited control and ownership over the lyrics and songs they create.


Nevertheless, if you're looking for an entertaining way to create songs on the fly, and even publish them to platforms like Spotify and Apple Music, you can do it. We recommend checking out their website to learn more!

bottom of page