The approach
Spatially aware generation.
A generated video can place a performer in a cathedral, an empty club or an open
field while the voice still sounds like a close, dry studio recording. The picture
describes a space, but the sound ignores it. That mismatch is one reason otherwise
convincing generated footage can still feel synthetic.
AKUSPACE closes that gap by re-generating the take with the acoustic character of
the scene. The performance returns inside the requested room or place, with its
timing preserved for synced video. It does not change the pixels; it makes the
picture and sound feel as though they belong to the same environment.
Beyond rooms and outdoor places, the same control surface reaches original Eurorack
modular treatments. This brings prompt-controlled sound effects into the same
workflow: a less explored direction for generative audio and video.
Where the material comes from
All training material is owned and was recorded or produced for the project over
several years. It includes multiple speaking voices, beats and electronic music,
percussion, and acoustic instruments.
The treatments come from digital reverbs, custom presets, original Eurorack
modular patches and original field recordings used for the outdoor beds. Together
they cover spaces, places and sound effects. Nothing was scraped, and no
third-party licensed audio was used for training.
How it is built
Every training item contains the same performance twice: once dry and once through
a real treatment chain. This teaches the model a transformation instead of an
association between particular sounds and particular environments.
Rooms and sound effects are represented at three trained amounts —
gentle, moderate and heavy. Outdoor places use
gentle and heavy. The level word occupies the same position in
every caption, giving the model a consistent semantic control rather than an
arbitrary number. The ComfyUI nodes emit those exact strings, so users select the
space and amount instead of guessing the wording.