ꜱᴇᴍɪʟʟᴀ ᴀ.ɪ. is an artistic research project that explores the techno-poetics of Mixe divination through “maiz throwing” and positions it as an interface for uncovering and exploring the “latent space” or multidimensional space within a generative neural network for audio synthesis.

It is a neural audio synthesis interface which employs the RAVE: Realtime Audio Variational Autoencoderas its primary engine for sound synthesis, focusing on the use of its decoder as a generative music tool.

Software interface is compatible with OS X and Windows 10 via the Max 8 runtime.

Included models in v1:

- Okachihuali
- Salterio
- Cumbus
- Liquid
- Darbouka



Download and installation instructions:
http://bi t.ly/ sem illaAI
(remove the spaces in the link)

Disclaimer:
The software version of ꜱᴇᴍɪʟʟᴀ ᴀ.ɪ. and RAVE is free, all donations will go toward future development of the project.

For troubleshooting and support write to:
hola@semilla.ai

More info:
semilla.ai
iil.is/research/semilla