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

# Review your dictation data

> Clean your dictation dataset before fine-tuning: fix transcripts, delete bad clips, export a training-ready manifest.

Rekody can save your dictations as training data. Review is the page where you clean that dataset: play each clip, fix its transcript, and end up with labels you trust.

Open it from the Mac app under **Settings → Dictation → Review your dictation data**, or from the terminal:

```bash theme={null}
rekody review
```

The page runs on your Mac at `http://127.0.0.1:7878`. Nothing about your audio or transcripts leaves the machine.

## The second opinion

On first run you choose how to review:

* **Get a second opinion** (recommended). Whisper large-v3 re-listens to every clip and flags where it disagrees with your saved transcript, so you review only the differences. It is a one-time 3.1 GB download from Rekody's model repository, checksum verified, and it runs entirely on your Mac.
* **Start from my transcripts**. No download. You read and fix each transcript yourself, and you can add the second opinion later.

## Reviewing a clip

Red words are your original, teal words are the suggested fix. Click any word to switch which one gets saved, then:

* **Save correction** (`S`) saves exactly what the WILL SAVE line shows.
* **Keep original** (`K`) marks the clip reviewed with no changes.
* **Edit text** (`E`) opens the transcript for free editing.
* **Delete clip** removes the audio and transcript from your dataset. It always asks first, and it always takes a click: deletion has no keyboard shortcut and cannot be undone.

Use the two dropdowns to filter by status and by how much the suggestion differs.

## Reviewing from your phone

Start the server with the network flag and open the printed address on a phone connected to the same Wi-Fi:

```bash theme={null}
rekody review --lan
```

Treat this as a trusted-network feature: while the server runs with `--lan`, anyone on your network can open, edit, and delete the dataset. The default (no flag) stays private to your Mac.

## When you finish

The done screen shows what changed and offers two paths: export `manifest.jsonl` for any training pipeline (your original files stay untouched), or send the dataset to Rekody's managed fine-tuning, which trains a model on your voice and vocabulary and delivers it back into the app.


## Related topics

- [Privacy and your data](/app/privacy.md)
- [Snippets](/app/snippets.md)
- [FAQ](/app/faq.md)
- [Your first dictation](/app/first-dictation.md)
- [Library](/app/library.md)