After careful consideration, we have made the decision to end support for AWS DeepComposer, effective 17-Sep-2025. New customer sign-ups and account upgrades are no longer available. Active customers will be able to use AWS DeepComposer and access compositions or models as normal until 17-Sep-2025, when support for the service will end. To help transition off this service, we have provided recommended steps and alternative services in the FAQs page.
Press play on machine learning
AWS DeepComposer gives developers a creative way to get started with machine learning. Get hands-on, literally, with a musical keyboard and the latest machine learning techniques, designed to expand your ML skills.
Get started with the AWS DeepComposer keyboard to create a melody that will transform into a completely original song in seconds, all powered by AI. Designed specifically to educate developers, AWS DeepComposer includes tutorials, sample code, and training data that can be used to get started building generative AI models, all without having to write a single line of code.
Creative meets generative
Generative AI is one of the biggest recent advancements in artificial intelligence technology because of its ability to create something new. It opens the door to an entire world of possibilities for human and computer creativity, with practical applications emerging across industries, from turning sketches into images for accelerated product development, to improving computer-aided design of complex objects. Until now, developers interested in growing skills in this area haven’t had an easy way to get started. Developers, regardless of their background in ML or music, can get started with Generative Adversarial Networks (GANs). This Generative AI technique pits two different neural networks against each other to produce new and original digital works based on sample inputs. With AWS DeepComposer, you can train and optimize GAN models to create original music.
Input a melody by connecting the AWS DeepComposer keyboard to your computer, or play the virtual keyboard in the AWS DeepComposer console.
Generate an original musical composition using the pre-trained genre models in the AWS DeepComposer console. Choose from rock, pop, jazz, classical, or build your own custom genre.
Learning at your fingertips
AWS DeepComposer allows developers of all skill levels to get started with Generative AI by providing hands-on tutorials to quickly start training models and test them in a fun, musical experience.
In addition to the physical keyboard, the AWS DeepComposer console includes a virtual keyboard so that you can compose and learn anywhere.
The AWS DeepComposer community provides an opportunity for you to meet with developers and creators like you.
Getting started with AWS DeepComposer
Explore the pre-trained sample models available in the AWS DeepComposer console, to create original and inspiring music.
Tweak the model hyperparameters such as epochs and learning rate in the AWS DeepComposer console or for advanced learning build your own custom GAN architecture with Amazon SageMaker.
Get creative and customize your AI-generated music using your favorite Digital Audio Workstation (DAW).
Upload your finished AI-generated compositions directly from AWS DeepComposer into SoundCloud to share your tracks with the world.
Tune in to learning capsules
Learning capsules provide developers with tutorials to learn Generative AI in easy-to-consume, bite-size modules. With learning capsules, developers can now get hands-on with Generative AI techniques in addition to ML concepts. Developers looking to dive deep will be provided with sample Amazon SageMaker notebooks for step-by-step code walk through in each learning capsule. Log on to the AWS DeepComposer console and tune in to learning.
The keys to machine learning
Get started by using the MIDI-compatible AWS DeepComposer keyboard to compose melodies as input for your ML generated compositions. Use the hardware buttons on the keyboard to control the volume, playback, and recording flow, as well as use the built-in functions to create more complex inputs. You can also export the MIDI files to your favorite Digital Audio Workstation (DAW) and get even more creative.
