> ## Documentation Index
> Fetch the complete documentation index at: https://superwhisper.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Crashes During or After Transcription

> Fix Superwhisper crashes during dictation or right after processing. Isolate the cause, then report it with logs.

Your dictations are safe: Superwhisper saves audio every few seconds while you record, so a crashed dictation is saved in [History](/docs/get-started/history) and can be reprocessed.

## Isolate the cause

<Steps>
  <Step title="Update first">
    **Settings → Configuration → Check for Updates**. Crash fixes ship in almost every release, and this resolves most reports.
  </Step>

  <Step title="Switch to a cloud model">
    If crashes happen with a local model, edit the mode and select a cloud **Voice Model**. Local models are the heaviest workload in the app. If the crash stops, your machine is running out of memory for that model. Try a smaller one like **Parakeet Multilanguage** (494 MB), or close other memory-heavy apps.
  </Step>

  <Step title="Simplify the mode">
    Test with the plain **Voice to Text** mode. If the crash only happens in one mode, the cause is that mode's model or context settings. Rebuild the mode one setting at a time.
  </Step>

  <Step title="Check free disk space">
    Local models and recordings need room. A nearly full disk causes failures mid-write.
  </Step>
</Steps>

## Report it

If it still crashes:

1. Turn on **Error logging** in **Settings → Configuration**
2. Reproduce the crash once
3. Follow [Report an Issue](/docs/get-started/history#report-an-issue). Include the app you were dictating into, the mode, and its models

If the current version is unusable for you, previous releases are listed at [superwhisper.com/appcast.xml](https://superwhisper.com/appcast.xml).