We've been through a couple years of what felt like warp-speed developments in AI music software. The history of these text-to-music apps can be traced back to a pivotal moment in April 2023, when WavTool's AI DAW debuted with a GPT-4 chat assistant. It was able to help compose midi, generate instruments, control effects, and run activities in the workstation through AI chat commands.
WavTool announced a new round of features in January 2024 that got us excited to revisit the app and revamp this article. Then in June 2024, they launched a new stem splitting product called SunoDAW (apparently without permission or direct affiliation with Suno) that pulls music in from third party sites and brings them directly into their browser DAW.
The company spun down their service on November 15th, 2024 with the promise that they would be returning soon. It appears that the company was acquired but there have been no official announcements yet and who bought them.
We're keeping this article up as a record of WavTool's best features.
Table of Contents
What is WavTool?
WavTool was an AI-powered digital audio workstation that loaded in browser. It included an embedded AI chatbot, called the Conductor, that could be conjured and put away at will. The GPT-4 powered assistant detected chords and understood audio production techniques. In this way, it acted as a kind of AI bandmate.
Here are some of the core features that came with WavTool, back when we first reviewed it back in May 2023.
AI Conductor - WavTool called their AI chatbot the Conductor because of its ability to guide users through the music making process. It could take action on any part of the DAW, generating MIDI and wavetables on request.
Browser app with cloud saving - WavTool projects were saved to the cloud, so you could open your projects up on any computer after logging in.
Custom Wavetables - Pull in one of WavTool's instrument presets for your MIDI track or build custom wavetables from scratch. The video above went into detail on how users can synthesize new instruments.
Device panel - WavTool's panel let you set up devices that control EQ, reverb, delay, dynamics, distortion, LFOs and side chain compression, visualizers and more. Unlike Ableton Max (a comparable tool), AI Conductor could create and edit devices from your text prompts.
QWERTY & MIDI Controller Support - WavTool's piano roll included a keyboard interface that showed you the notes you were playing. You could play on a QWERTY computer keyboard or use a standard MIDI controller.
WavTool features in 2024 before they shut down
Many of our readers will be familiar with WavTool's classic features listed above, but might not have kept up with more recent developments. They maintained an impressive monthly cadence with several new features released. Let's have a look at the timeline below and see what their Library had to offer.
Wavtool rolled out a new Skills interface in October 2023 that included a number of special AI features and workflows:
Generate short loops: Turn your musical ideas into five-second samples using WavTool's text-to-music generator
Humanize Clip: Quickly add rhythm and velocity variation
Convert to MIDI: Convert audio to MIDI with controls to fine-tune the conversion in real time
Stem Splitter - Audio clips could be split into vocals, drums, bass, and any remaining sound. This made it easier to remove background noise from rough recordings and create a mixable, multitrack project. It's more convenient than toggling between their app and other AI stem splitters.
Song Sharing URLs were introduced in November 2023, making it possible to host music on a public URL and share with others. Just select the song section you want to share and click Export -> To Song Page. Name the track, generate a link, and you were good to go.
Prototypes were introduced in December 2023, delivering a popular AI music feature called Timbre Transfer that captured the sound of one instrument and applies it to any audio clip. They offered a handful of output sounds to experiment with as well as the option to train your own sound models.
Some major updates came out in January 2024, improving on existing skills and introducing a DAW bridge that let you load your plugins into the browser app!
Voice Model (Prototype) Training - Users could now create their own custom Prototypes (train an AI model) for any consenting voice, and any non-voice sound.
Non-voice models had all vocal sounds removed from them prior to training, and voice models were only trained if the words spoken in the training data substantially matched a time-limited unique AI-generated training script.
Due to the verification requirement, it was possible to train a voice model from pre-existing recordings of a person speaking or singing.
Skills Refresh - Skills were added to the Library panel and could be opened simultaneously, allowing for a seamless and dynamic workflow. Drag and drop skill inputs and outputs into a project or between skills.
Conductor Upgrade - Conductor could now chain together multiple AI processing steps/Skills. For example, the prompt “Make some disco music, convert the bass line into MIDI, and add some alternate chords to it” triggered the following Skills:
AI text-to-audio sample generation for ‘Disco Music’
Stem Split to pull out the bass line
Audio-to-MIDI conversion of the bass line
Composer suggests a new set of MIDI notes above the bass line
These were great, but as a text-to-MIDI plugin company ourselves, we were particularly giddy to find out that WavTool now offers Plugin Support. This was a massive step forward for them and helped to legitimized them as a DAW.
How to load any audio VST in WavTool
To get started, you needed to install the WavTool Bridge, a small plugin host that allowed anyone to connect their installed plugins.
Install the plugin bridge and boot it up. You would see the WavTool icon on your computer's top navigation menu, next to any other open applications.
Open the Library panel in WavTool and select the Plugins & Devices tab.
Scan your existing library and the plugin bridge will go through your local computer to find all of the plugins
Once the scan was complete, double click on the plugin you wanted to load
In the example below, we loaded the AudioCipher text-to-midi plugin. After typing in a test phrase and dragging the MIDI into the arrangement view, there was a short loading period of a few seconds. Just moments later, the MIDI notes were there as expected!
The DAW bridge file was only a few megabytes large and we were able to install it without any difficulties using a Macbook pro. Each plugin ran in a sandboxed environment, meaning errors in the plugin did not affect the rest of the user’s session. This is a big perk, as many of the most advanced DAWs have been known to crash if a plugin hits a critical bug.
Conductor chatbot: AI music composer
WavTool's AI music composer, the Conductor, leveraged the conversational intelligence of GPT-4 to have deep and nuanced conversations with you about any musical topic. But its real talent was the ability to turn around and take action in the DAW, based on commands from GPT. This text-to-music feature was something we had never seen before.
There's one very exciting thing about Conductor that sets the AI DAW apart from the other major AI MIDI generator apps. Unlike Google and OpenAI's MIDI generators, WavTool knew why it generated MIDI in a particular way and explain its reasoning to you in detail. You just had to ask!
Previous MIDI generators had not been set up to engage conversationally or take text commands. This meant that we never knew why the AI was generating a particular MIDI melody or chord progression. It was not possible to critique and fine tune its choices over time, other than requesting variations.
Prompting tips for the WavTool MIDI generator
As a WavTool user, you didn't need be an amazing writer or "prompt engineer" to get started. That being said, the words you used with the AI would dictate the quality of its creations and the quality of your experience.
A fair warning for any music theory heads out there - WavTool's conductor cannot currently turn requests for a specific chord progression or melodic shape into MIDI. Instead, try to keep your requests limited to more general moods and styles.
Pricing: How much does WavTool cost?
WavTool had a Free tier with a limited number of AI prompts, which posed restrictions on the length and number of tracks in your production. They later revamped their pricing to allow all users to access features expected of a DAW. They also had a free 2-week trial for the Pro tier.
Final Thoughts on WavTool & the future of AI DAWs
Generative audio workstations and AI DAWs are two different names for the same basic idea. They stand in contrast to what could be called AI VSTs, or third party plugin / standalone apps that run AI services to augment a DAW.
There are a few other AI-powered audio workstations, like Logic Pro's AI session musicians, the audio-to-midi RipX DAW, and a still unreleased Deepmind Lyria program by Google.
In this new landscape, our musical vocabulary will be an asset. Writers may gain a competitive advantage in music that they've never enjoyed before.
Melody generators and chord progression software could also be in the line of fire, if these AI DAWs become sufficiently advanced. Why would you pay for a random note generator when your AI music composer can do it for you?
That being said, GPT-4 still has some ways to go before it actually poses a threat to MIDI generation software. Producers are attached to their existing DAWs and workflows. The quality of GPT's musical output also needs to get better in order to claim the throne.