// 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

Where config.json lives depends on whether you run the installer build or a source checkout.

Installer buildPath
Windows%LOCALAPPDATA%\LiveAudio\data
Linux~/.local/share/liveaudio/data
Source / devPath
Windows%APPDATA%\LiveAudio
Linux~/.config/liveaudio

With the launcher, the data home is <root>/data unless you set LIVEAUDIO_HOME to point somewhere else. When the app runs without the launcher (a dev checkout), it defaults to %APPDATA%\LiveAudio / ~/.config/liveaudio, and a legacy config.json left in the current working directory is migrated automatically on first load.

Portable mode: create an empty portable.marker file next to the launcher and the root becomes <launcher dir>/data, so config, sessions and models all stay beside the app instead of in the per-user locations above. In this mode HF_HOME is also redirected into the portable folder, so downloaded Whisper models live on the same drive — ideal for a USB stick.

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
}