// docs / troubleshooting
Troubleshooting
Root-cause fixes for the most common setup issues — capture, CUDA, the WebSocket connection, and Python-version upgrades — followed by the local-first diagnostics export.
Captions are not appearing
Verify the selected audio device in the panel. If you are capturing desktop sound on Windows, make sure you enabled the correct WASAPI loopback channel.
CUDA error / out of memory
LiveAudio monitors VRAM before each transcription. When free memory drops below about 500 MB it frees the CUDA cache automatically and surfaces “GPU saturada - VRAM baja”. If it still fails: switch the inference device from cuda to cpu, or load a smaller model (tiny or base), and close other VRAM-heavy programs (OBS with NVENC, games). Updating your NVIDIA driver resolves most CUDA runtime failures.
Upgrading from the Python version (v1.0.0–v1.2.7)
v1.5.0 replaces the Python builds with a native Rust + Tauri 2 app. The installer detects legacy installs through the Windows registry (32- and 64-bit views), runs the old uninstaller silently (NSIS and Inno Setup), stops leftover processes, and removes the obsolete Python folders — while your settings and sessions in %APPDATA%\LiveAudio are preserved.
OBS does not connect
Make sure the engine is running — port 8765 must be listening. If your firewall or antivirus blocks local traffic, add a rule to allow localhost connections on the WebSocket port.
Installer reports a running copy
Close every LiveAudio window first — the v1.5.1 installer stops leftover Python-era processes automatically, but stop a transcription in progress from the app (Stop Transcription) before upgrading.
Audio cuts out or long silences
Increase the silence detection value (around 1.0–1.5 s) so heavily paused phrases are not cut mid-sentence.
Windows SmartScreen warning
Install & download recovery
Most install problems are fixed by re-running the installer — it repairs the app and preserves your settings and sessions:
| Problem | What to do |
|---|---|
| Interrupted model download | Just relaunch the app. Downloaded models are cached, so only the missing pieces are fetched again. |
| Installer warns about a running copy | Close every LiveAudio window (stop transcription first), then run the installer again. |
| Corrupted install | Re-run LiveAudio_1.5.1_x64-setup.exe — it repairs the install and keeps %APPDATA%\LiveAudio intact. |
| Coming from the Python version | The installer removes legacy v1.0.0–v1.2.7 builds automatically and preserves your settings. |
| Where are the logs? | The in-app Event Log records the service lifecycle, config changes and diagnostics. |
Local diagnostics
LiveAudio ships local-first diagnostics — no telemetry is sent anywhere. Use them when OBS stops receiving subtitles, the ASR falls behind, or audio reconnects too often.
- How: reproduce the issue, click Export diagnostics in the app, then review the exported JSON (process states, queue sizes, audio/asr/ws states).
- Privacy: the export never includes raw audio or full transcripts, and it sanitizes secrets, tokens and sensitive paths.
| Key | Value |
|---|---|
diagnostics_enabled | true / false |
diagnostics_level | minimal / deep |
diagnostics_export_dir | path or null |