// docs / config

Configuration

LiveAudio writes a config.json with sensible defaults on first run. Change everything from the GUI, or edit the file directly. This page is the full key reference.

File location

v1.5.1 keeps your settings and sessions under %APPDATA%\LiveAudio on Windows — the installer preserves this folder when it removes legacy Python builds.

BuildPath
Windows x64 (v1.5.1, Rust)%APPDATA%\LiveAudio
Linux (legacy Python v1.2.7)~/.local/share/liveaudio/data

Portable: prefer no install? Run liveaudio-desktop.exe (~16.2 MB) — the standalone Windows build needs no setup.

Options

KeyTypeDescription
output_dirstringPath to the sessions folder.
devicestring"cuda" or "cpu".
cpu_threadsnumberNumber of CPU threads for inference.
model_sizestring"tiny", "base", "small" or "turbo".
blackliststringComma-separated filter words (see the getting-started blacklist).
continuous_sessionbooleanKeeps the same session across restarts.
subtitle_stylestringdefault, karaoke, neon, minimal, bold, rgb, typewriter.
subtitle_backlog_policystring"auto", "live_only" or "send_all".
subtitle_max_live_delay_secnumberMax delay before OBS hides backlog.
subtitle_catchup_interval_secnumberPacing between backlog items.
silence_timeoutnumberSeconds of silence before cutting a segment.
max_chunk_durationnumberMax seconds before forcing a cut.
audio_devicestring | nullSelected device, or null for the system default.
selected_profile_idstring"fast", "balanced", "quality" or "stable".
profile_modestring"preset" or "custom" — set to "custom" automatically when you edit a built-in profile.
ws_portnumberWebSocket server port (default: 8765).
obs_enabledbooleanEnable or disable sending subtitles to OBS.
whisper_context_prompt_enstringOptional initial-prompt context passed to Whisper for English (e.g. recurring names or jargon). Empty by default.
whisper_context_prompt_esstringSame, for Spanish. Empty by default.
asr_languagestringLanguage code for Whisper (e.g. "en", "es").
settings_navigation_modestringSettings UI layout — "tabs".
diagnostics_enabledbooleanEnables local diagnostics instrumentation.

Example config.json

config.json
{
    "output_dir": "C:\\streams\\sessions",
    "device": "cuda",
    "cpu_threads": 8,
    "model_size": "small",
    "blacklist": "amara.org, subtítulos por, gracias por ver",
    "continuous_session": true,
    "subtitle_style": "default",
    "subtitle_backlog_policy": "auto",
    "subtitle_max_live_delay_sec": 10.0,
    "subtitle_catchup_interval_sec": 1.5,
    "silence_timeout": 0.8,
    "max_chunk_duration": 5.0,
    "audio_device": null,
    "selected_profile_id": "balanced",
    "profile_mode": "preset",
    "ws_port": 8765,
    "obs_enabled": true,
    "whisper_context_prompt_en": "",
    "whisper_context_prompt_es": "",
    "asr_language": "en",
    "settings_navigation_mode": "tabs",
    "diagnostics_enabled": false
}