Av3ry

Av3ry is an AI program and a virtual persona, who is composing music, communicating with people and learning from interactions.

The main component is the on-demand conversation and art generation of the bot. The goal is to create unique pieces of music and art in the given moment - and based on the criteria of the user interaction.

In the idle process, when not communicating, the system generates random exports and creates a database of 10,000 music pieces. Furthermore the system running on its own creates a continuous audio stream broadcasted live 24/7. It is continuously evolving and changing musical progression.

#A

For their first album on Audiobulb Av3ry presents #A - 99 musical outputs.

Cat: AB0101

Release date: October 2020

 

Reviews

  1. Headphone Commute

    If you really want something “out there,” look no further then a new release by Audiobulb composed by a non-binary virtual persona named Av3ry. Now, I’ve heard my share of generative, artificial intelligence and machine music, and most of it is just ‘meh.’ I think one exception can be made when talking about ambient music, as quantized chimes, swells, and swooshing noise can lul even this non-believer to sleep. But Av3ry is something else entirely. They not only create music but also communicate with their audience, feeding the input back into the compositional process. The system generates random exports from external sources (Soundcloud, Freesound, YouTube, etc.), systematically processes them using Max/MSP, interleaves conversational extracts, and then uploads the work to its online archive. And the music is just strange. Think abstract post-techno breaks mixed with text-to-speech poetry, swirling atmospheric textures, and mashed-up rhythms, that somehow continue to hypnotize me and keep me engaged. I think it’s the culmination of sound-driven genres that for some reason reminds me of ArcaAndy Stott, and even World’s End Girlfriend [like the Tibetan singing bowls being punctured by a distorted hardcore kick] with the sheer number of ideas and at the same time minimalism and space. If you want Av3ry to write you a piece of music, head over to av3ry.net for instructions to chat with the bot and give them parameters for your sounds. I asked for a soft long-evolving slow piece and got a nightmarish hallucination of snippets that would easily impress a video game composer searching for inspiration for their new horror soundtrack. A little uneasy and freaky indeed.

  2. 909 Originals

    According to the official blurb, ‘Av3ry combines natural language processing, algorithmic composition, data crawling and machine learning. She*he is constantly operating and creating music, poems and pictures in the moment – based on communication with interacting users. The music pieces are based on the criteria specified by the users. So the result is instant and individual – and sent directly to a single user.

    ‘The program extracts key features from the description of the users and tries to generate the pieces accordingly. Through the feedback of the users after listening to the result the algorithm can learn and fine-tune its parameters.’

    Next month, Av3ry is set to put out her (his?) first album, a collection of close to 100 intriguing electronic compositions, on Audiobulb Records, a label renowned for its ‘exploratory’ music concepts.

    The album, Av3ry presents #A – 99 musical outputs, is part Aphex Twin, part Philip Glass, part Commodore 64, and features tracks with titles such as 9174b, 12377, 12934, 9191a, and the fantastically named symbol12asdasd234234893.

    For any Hitchhiker’s Guide to the Galaxy fans out there, there’s also a track entitled 42 – as to whether it reveals the meaning of life, well, you’ll have to listen and find out.

    Av3ry presents #A – 99 musical outputs is released on 21 October 2020, on Audiobulb Records. Open the pod bay doors, Hal…