Text-to-Audio
Stable Audio Tools
Safetensors
English

Android + OpenCL implementation β€” latent-diffusion audio on-device on non-flagship phones (Adreno 6xx)

#6
by a8nova - opened

Hi! I wanted to share an Android + OpenCL implementation of Stable Audio Open Small, in case anyone wants to run it on a phone:

  • Try it: Edgi on Google Play β€” runs fully on-device, no cloud.
  • Open source: the app is built on top of the open-source adreno-llms inference engine β€” https://github.com/a8nova/adreno-llms β€” pure C++/OpenCL with hand-written kernels tuned for Adreno, running the whole pipeline on the GPU: T5 conditioning + 8-step DiT + VAE decode.

It's tuned and tested on Adreno 6xx GPUs β€” the GPU class in mid-range and older Android phones (verified on a 2020 Motorola Razr / Adreno 620) β€” and should run on most arm64 Android phones with OpenCL, though the optimizations are Adreno-specific. On the Adreno 620 it generates an 11 s stereo 44.1 kHz clip in ~100–130 s (thermal-dependent) β€” to my knowledge one of the first latent-diffusion audio models running fully on a mid-range phone GPU.

Hope it's useful β€” happy to answer questions!

Sign up or log in to comment