We are in the era of generative AIs. ChatGPT has only been the beginning of many programs that today are tools that help to perform many jobs, although for others it is just a software to tinker with. The funny thing is that the developers extend this art to unsuspected limits, like this AI that turns text into songs for you.
The operation of the application is very simple. So much so that if you’ve already tinkered with ChatGPT or other artificial intelligence apps, you can get just a small idea of ​​the possibilities it can offer you, especially if you make music. Whether they are instruments or musical genres, the application will give you a new audio track or new melody created from the text that you suggest to the application itself. The results may surprise you
TextToSample, an AI that makes music with whatever you ask
Interacting with artificial intelligence is very simple today. Following the example of ChatGPT, you only have to write a question and immediately afterwards it will give you an answer with the Internet results it has found but explained in its own way. Keep in mind that the free version has its limitations, but there is no doubt that it is a very important tool for the future of search engines as Bing Chat has already shown.
What is more important is that there are many ingenious programmers who are capable of doing wonders and a clear example is TextToSample. This artificial intelligence, created with the open source MusicGen AI, is the clearest example. What its creators have achieved is an application with which to create all kinds of music just by typing what you need in its search box.
How to use TextToSample
As you can see in the video, the interface is very simple and concise. The first data input you need to make it work is the use of the text box. You will have to write what you want, either a melody of a specific genre, the use of a specific instrument or mix both things as it gives you a melody without the use of a family of instruments.
Best of all, you can add audio tracks, whether they are created by artificial intelligence itself or that you have saved. Afterwards, you only have to add the duration of the audio track and generate the new music, a process that will take a few seconds. You can then listen to the result and remix it again to see what you can do with it.
Every time you use it you will have a small history with which you can download all the audio tracks generated in a session. They will all be different at all times, so if there is one that you like, do not hesitate to resort to that history to download it at the moment.
An app with bugs to polish
Although it is a generative AI, the samples it gives TextToSample they will not be able to cover the benefits offered by human ingenuity or its ability to improvise. This is something that the guys at Samplab are quite clear about, who have a lot of work to do when it comes to polishing the code.
The app is very new and some things you ask of it may not be generated correctly. For this reason, the work you do on the application will make it much better and complete, but it is also part of the company itself to add several updates in order to solve all the bugs that, as we mentioned, will end up appearing. Plus, it’s free, so you won’t have to pay to get the tracks you need at least for now.
