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

# Local transcription isn't working

> Whisper or Parakeet failing on your own machine — models, GPU acceleration, and the per-mode setting people miss.

You've chosen a local model and transcription fails, falls back to the cloud, or
produces nothing.

<Warning>
  **Check this first.** The transcription engine is set **per mode**. Dictation,
  note recording and audio upload each have their own — so switching one to
  local leaves the others exactly where they were.

  **Settings** → **Speech-to-Text** under **AI Models**, then the tab for the
  mode you're actually using: **Dictation**, **Note Recording** or **Audio
  Upload**.

  If you changed the setting and nothing changed, this is almost always why.
</Warning>

## Quick checks

<Steps>
  <Step title="Confirm a model is downloaded">
    Local transcription needs the model on disk. The model picker shows which
    are installed. If a download failed, see
    [A model won't download](/help/fix/model-download-fails).
  </Step>

  <Step title="Check the mode you're using is set to local">
    As above — the right tab, not just the right section.
  </Step>

  <Step title="Try a smaller model">
    Large models need substantial memory. If a small one works and a large one
    doesn't, that's the constraint, and the smaller model is a real answer
    rather than a workaround.
  </Step>

  <Step title="Check bundled components weren't quarantined">
    Security software removing whisper.cpp, sherpa-onnx or FFmpeg breaks local
    transcription specifically while leaving everything else working. See
    [Antivirus blocks OpenWhispr](/help/fix/antivirus-blocks-openwhispr).
  </Step>
</Steps>

## GPU acceleration

If GPU acceleration fails — an unsupported card, or not enough video memory —
OpenWhispr **restarts on the CPU, retries the same request, and tells you it's
using CPU instead**. Your dictation still completes; it's slower.

If that happens every time, turn GPU acceleration off from the GPU card in the
transcription model picker. It removes the failed attempt and the delay it adds.

## What "local" does and doesn't need

* **No network** once the model is downloaded — as long as cloud fallback
  (below) is off, which is the default.
* **No plan allowance** — local transcription doesn't count against your weekly
  words on any plan.
* **Real CPU or GPU work** — so it's slower than cloud on modest hardware, and
  a laptop on battery may throttle it.

[Cloud vs local](/guides/cloud-vs-local) sets out the trade-offs;
[Local models](/guides/local-models) covers the models themselves.

## FAQ

<AccordionGroup>
  <Accordion title="It falls back to the cloud on its own.">
    That only happens if cloud fallback has been enabled — it defaults to
    off, so out of the box a failed local attempt just fails rather than
    silently going to the cloud. If you're seeing this, a debug log will show
    what's configured and why the local attempt failed — see
    [how to send one](/troubleshooting#send-us-a-debug-log).
  </Accordion>

  <Accordion title="Local is much slower than cloud.">
    Expected on most machines. A smaller model is the usual answer if speed
    matters more than the last few points of accuracy.
  </Accordion>

  <Accordion title="Which languages work locally?">
    It depends on the model — Whisper and Parakeet support different sets.
    [Local models](/guides/local-models) has the detail.
  </Accordion>

  <Accordion title="Is local really private?">
    Local transcription runs on your machine and the audio doesn't leave it —
    as long as cloud fallback is off, which is the default for every install.
    If it's been enabled, a failed local attempt sends that audio to the
    cloud instead of failing.
    [Cloud vs local](/guides/cloud-vs-local) sets out what each mode sends.
  </Accordion>
</AccordionGroup>

<Snippet file="still-need-help.mdx" />

## Related

* [Local models](/guides/local-models)
* [A model won't download](/help/fix/model-download-fails)
* [Nothing was transcribed](/help/fix/nothing-was-transcribed)