// docs / getting-started

Getting started

Two ways to run LiveAudio v1.5.1 on Windows: the prebuilt installer (recommended) or the portable standalone exe. No Python installed, no runtime to provision — the app is a native binary.

Option A — Installer (recommended)

Download the latest release from GitHub Releases:

Windows x64: LiveAudio_1.5.1_x64-setup.exe (graphical installer, ~26.2 MB).
Windows portable: liveaudio-desktop.exe (~16.2 MB) — standalone, no install.
Linux: legacy LiveAudio-1.2.7-linux-x64.tar.gz — extract, then run ./liveaudio-launcher.

The first run downloads transcription models and auto-detects your GPU. Later runs start instantly. Coming from v1.0.0–v1.2.7? The installer removes the legacy Python build silently and preserves your settings in %APPDATA%\LiveAudio.

Option B — From source (developers)

Developer path — clone the repo and follow the build instructions in the repository README (Rust toolchain + Tauri 2 prerequisites).

bash

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

# Developer path: see the repository README for the
# Rust + Tauri 2 build prerequisites, then build from source.

Verify the install

Open the app — the header shows the live status (listening / VAD state) and the Advanced tab shows the active compute device (CUDA or CPU). Speak, and captions appear in the live subtitle feed and stream to OBS.

Updates & recovery

v1.5.1 configures everything from the GUI — the Advanced tab picks the compute device (CUDA/CPU) and model without a restart. Updates arrive in one click from inside the app. If an install ever breaks, re-run LiveAudio_1.5.1_x64-setup.exe: it repairs the install and preserves your settings and sessions in %APPDATA%\LiveAudio.

GPU auto-detection

On startup LiveAudio checks for an NVIDIA GPU. If one is available it defaults to cuda; otherwise it falls back to cpu automatically. CUDA needs driver ≥ 525 and VRAM ≥ 4 GiB — no manual configuration required.

Profiles

Profiles are FPS-aware presets. Editing a built-in profile turns it into Custom; changes only take effect after you click Apply changes.

Profile	Recommended for
`Fast`	Lowest latency and short phrases.
`Balanced`	Recommended for most sessions.
`Quality`	Higher accuracy, more VRAM and latency.
`Stable Streaming`	Reduces GPU load while gaming or streaming on a busy PC.

Hallucination blacklist

Whisper can invent phrases during silence. LiveAudio filters them with an editable blacklist. The default list (from config.json.example) is:

config.json.example · blacklist

amara.org, subtítulos por, suscríbete, dale like, gracias por ver,
memos, gracias, activar la campanita, ¡Hasta la próxima!, por favor

Words and phrases are comma-separated and fully editable from the Subtitles tab — add the filler your stream tends to hallucinate, or clear entries you want to keep.

Models

Pick a model in the Model & Hardware tab. Larger models are more accurate but slower and use more VRAM; each one downloads once on first use, then runs offline.

Model	First-run download	Notes
`tiny`	~150 MB	Fastest; good on low-end CPUs.
`base`	~300 MB	A step up in accuracy, still light.
`small`	~480 MB	Balanced default for CPU.
`turbo`	~1.5 GB	Highest accuracy here; best on a GPU.

Session files

Every session is saved to disk as a transcript (transcript.jsonl) and WebVTT subtitles (subtitles.vtt), plus a session.json manifest:

sessions/

sessions/
└── session_2026-05-04_143022/
    ├── subtitles.vtt
    ├── transcript.jsonl
    └── session.json