> ## 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.

# "LLM Processing Error"

> Fix the "LLM processing error" in Superwhisper. Your transcription is safe in History; the AI formatting step failed.

**"LLM processing error"** means the transcription worked but the AI processing step (the language model that formats your text) failed. Your words aren't lost: the raw transcription is saved in [History](/docs/get-started/history), and you can [reprocess it](/docs/get-started/history) once the cause is fixed.

## Fix the error

<Steps>
  <Step title="Check your connection">
    Most language models run in the cloud, even in modes with a local voice model. If you're offline, switch the mode's **Language Model** to a local one like **S1-mini** or reconnect.
  </Step>

  <Step title="Retry from History">
    Open the dictation in **History** and reprocess it. Transient provider errors clear on retry.
  </Step>

  <Step title="Switch the language model">
    Edit the mode and pick a different **Language Model**. If the error follows one specific model, that provider is the problem.
  </Step>

  <Step title="Update Superwhisper">
    **Settings → Configuration → Check for Updates**. Provider API changes are fixed in app updates.
  </Step>
</Steps>

## Errors with your own API keys

If the failing model is one you added under **Settings → Models library → Bring your own keys**:

* **Re-check the key**: paste it fresh from the provider's dashboard. Expired or project-scoped keys fail with connection errors.
* **Google Gemini keys that start with `AQ.`**: update to the latest Superwhisper version, then re-add the key.
* **Check provider status**: an outage at the provider shows up in Superwhisper as a processing error.

Built-in cloud models need none of this. If you don't need your own keys, switch the mode back to a built-in model.

## Report it

Turn on **Error logging** in **Settings → Configuration**, reproduce the error once, and email [support@superwhisper.com](mailto:support@superwhisper.com) with the mode name and the model it uses.