Activate LiveAudio in four real steps.

ACTIVATION SEQUENCE

1. 01

   // get

   Get LiveAudio — installer, portable, or source.

   Most people just download and run. Three real paths: the graphical installer (recommended), the portable standalone exe, or building from source if you are a developer.

   Linux: legacy v1.2.7 build

   // installer

   Installer (recommended)

   Windows x64: download LiveAudio_1.5.1_x64-setup.exe and run it — no Python to install, the app is a native Rust binary. Coming from v1.0.0–v1.2.7? The installer removes the legacy Python build silently and preserves your settings in %APPDATA%\LiveAudio. Prefer no install? Grab liveaudio-desktop.exe (~16.2 MB) and just run it. Linux: use the legacy v1.2.7 tarball for now.

   windows x64Copy

   # Installer (recommended) or portable:
   LiveAudio_1.5.1_x64-setup.exe
   liveaudio-desktop.exe
   

   Windows: not code-signed yet

   // source

   Build from source (Rust + Tauri 2)

   Clone the repo and follow the build instructions in the repository README (Rust toolchain + Tauri 2 prerequisites). This path is for developers; everyone else should use the installer.

   git · developersCopy

   git clone https://github.com/plynte-labs/LiveAudio.git
   cd LiveAudio
   

   Legacy Linux tarball (v1.2.7) needs libportaudio2 (sudo apt install libportaudio2).

2. 02

   // first-run

   First run fetches the models.

   The first launch downloads the transcription models, then caches them. Models download on first transcription. Every later start is instant and fully offline.

   First run: internet required

   No Python, no pip chain: the installer (~26.2 MB) is the whole app. Your settings and sessions in %APPDATA%\LiveAudio survive updates and the Python-to-Rust migration.

3. 03

   // detect

   LiveAudio auto-detects your GPU.

   A GPU is optional — the CPU works. On launch, LiveAudio checks for a usable NVIDIA CUDA GPU and falls back to CPU automatically. You can always override the choice.

   • CUDANVIDIA driver ≥ 525 and VRAM ≥ 4 GiB → CUDA is used.
   • CPUNo usable GPU → CPU is used automatically. No setup needed.
   • overrideYou can force CPU or CUDA yourself before starting.

   GPU optional; CPU works. CUDA needs driver ≥ 525, VRAM ≥ 4 GiB.

4. 04

   // go

   Pick a profile, then START SYSTEM.

   Choose an FPS-aware profile, pick your audio device and CPU/CUDA + model, click Apply changes, then START SYSTEM. Speak — captions appear and stream to OBS over the local WebSocket.

   • Fastlow latency
   • Balancedrecommended
   • Qualityhigher accuracy, more VRAM
   • Stable Streamingreduces GPU load while gaming

   Editing a built-in profile creates a Custom one. Apply changes to activate.