sonicLAB has announced an update to its utility software that offers Large Language Model AI assistance to move sound objects in a virtual 3D acoustic space. Version 2 of SPATAI adds various new features.
It translates in real time the movement of multiple objects in cartesian or polar coordinates and sends this movement data to other 3D audio spatialization software. SPATAI is designed to overcome the creative limitations of traditional slider-based L/R, F/B, Elevation controls.
Changes in SPATAI v2
- SPATAI can now run both Local LLM on your current machine and also using the Cloud AI API; as selected by the user. The former does not consume tokens but needs an equivalent computer.
- The manual has an Appendix section which describes how to install Ollama and LMStudio both for OS X and Windows which can run the downloaded LLM’s on your machine.
- More products are added to be targeted via OSC: TimaxSpatial, L-acoustics (L-ISA), SpatRevolution (FLUX).
- ADM-OSC, a standard suggested for OSC communication in Spatial Audio industry, has been implemented as well.
- Cosmosf Saturn, sonicLAB’s advanced stochastic synthesizer which can render up to 7th order ambisonic output in realtime, can be addressed directly as well.
- CSV exporter: One can extract the object coordinate data between loop start and end points and export as a CSV format file.
- Added an Object ID shift value field: This value will be added to the OSC message ID of each object.
- A general settings panel has been added to set the OSC msg send rate, OSC IP address, LLM URL address, LLM model name.
- All value text fields can be edited and updated even when SpatAI is performing.
- Submitting new prompts will not interrupt the app actions. You can still perform existing animations while waiting for the prompt response.
Priced £15 GBP, SPATAI is available as standalone software for Windows and Mac and in VST/VST3 and AU plugin formats. The update is free for existing users.
More information: sonicLAB
