PyTorch in the Nix env is CPU-only, so the bundled omnivoice.cpp
runtime (ggml Vulkan) is the only GPU path.
Put vulkan-tools on the backend PATH: the app finds the adapter by
running `vulkaninfo` and otherwise reports none, since NixOS has no
FHS library directories for its fallback probe.
Default OMNIVOICE_GGUF_BACKEND=vulkan so the runtime opens the GPU or
fails loudly instead of falling back to the CPU. Overridable.
Refs: nix-overlay-ltr
The app's first-run setup downloads uv's generic CPython into
~/.config/VoiceStudio/runtime, which NixOS cannot execute (stub-ld).
Do the same frozen `uv sync` at build time against upstream's nixpkgs
python, in a fixed-output derivation, and point the app at it through
OMNIVOICE_BACKEND_CMD so it no longer manages a runtime of its own.
The ctranslate2 executable-stack flag is cleared at build time with
upstream's own repair, since the store is read-only.
CPU torch only. Adds an import-probe check.
Refs: nix-overlay-2r3
VoiceStudio ships its own flake that builds the Electron app, the Rust
dictation helper and the OmniVoice GGUF runtime. Re-export it instead of
repackaging: its package needs electron_44-bin, which our pinned nixpkgs
lacks, so the input keeps its own nixpkgs rather than following ours.
Build and upstream's six packaging checks pass on x86_64-linux.
Refs: nix-overlay-kk7