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

# Manual Model Installation

> Install transcription models manually when in-app downloads fail on corporate or restricted networks.

If model downloads fail inside Vowen with an error like **"Failed to download model: self signed certificate in certificate chain"**, your network is most likely intercepting secure connections. This is common on corporate networks that use SSL inspection tools such as Netskope or Zscaler.

The good news: your browser trusts your company's security certificates, so you can download the models yourself and place them in Vowen's models folder. Vowen picks them up on the next launch.

## Step 1 — Open Vowen's Models Folder

First, quit Vowen completely (right-click the tray icon and choose Quit).

<Tabs>
  <Tab title="Windows">
    Press <kbd>Win</kbd> + <kbd>R</kbd>, enter the following, and press Enter:

    ```
    %APPDATA%\Vowen
    ```

    Inside that folder, open the `models` folder. If it doesn't exist, create a new folder named exactly `models`. The full path looks like:

    ```
    C:\Users\<you>\AppData\Roaming\Vowen\models
    ```
  </Tab>

  <Tab title="macOS">
    In Finder, press <kbd>Cmd</kbd> + <kbd>Shift</kbd> + <kbd>G</kbd> and go to:

    ```
    ~/Library/Application Support/Vowen/models
    ```

    If the `models` folder doesn't exist, create it.
  </Tab>
</Tabs>

## Step 2 — Download the Model You Need

### Whisper Models

Each link downloads a single `.bin` file — no extraction needed. The same files work on Windows and macOS.

| Model          | Size   | Download                                                                                                     |
| -------------- | ------ | ------------------------------------------------------------------------------------------------------------ |
| Tiny           | 78 MB  | [ggml-tiny.bin](https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-tiny.bin)                     |
| Base           | 148 MB | [ggml-base.bin](https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.bin)                     |
| Small          | 488 MB | [ggml-small.bin](https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin)                   |
| Medium         | 1.5 GB | [ggml-medium.bin](https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-medium.bin)                 |
| Large v3       | 3.1 GB | [ggml-large-v3.bin](https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3.bin)             |
| Large v3 Turbo | 1.6 GB | [ggml-large-v3-turbo.bin](https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3-turbo.bin) |

English-only variants (slightly better if you only dictate in English):

| Model            | Size   | Download                                                                                           |
| ---------------- | ------ | -------------------------------------------------------------------------------------------------- |
| Tiny (English)   | 78 MB  | [ggml-tiny.en.bin](https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-tiny.en.bin)     |
| Base (English)   | 148 MB | [ggml-base.en.bin](https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin)     |
| Small (English)  | 488 MB | [ggml-small.en.bin](https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.en.bin)   |
| Medium (English) | 1.5 GB | [ggml-medium.en.bin](https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-medium.en.bin) |

### Parakeet Models

Parakeet downloads as a `.tar.gz` archive that you extract yourself. The archives are different per platform — make sure you grab the right one.

<Tabs>
  <Tab title="Windows">
    | Model       | Size   | Download                                                                                               |
    | ----------- | ------ | ------------------------------------------------------------------------------------------------------ |
    | Parakeet v3 | 501 MB | [parakeet-tdt-0.6b-v3-int8.tar.gz](https://assets.vowen.ai/models/parakeet-tdt-0.6b-v3-int8.tar.gz)    |
    | Parakeet v2 | 473 MB | [parakeet-tdt-0.6b-v2-int8.tar.gz](https://assets.vowen.ai/models/v2/parakeet-tdt-0.6b-v2-int8.tar.gz) |
  </Tab>

  <Tab title="macOS">
    | Model       | Size   | Download                                                                                                   |
    | ----------- | ------ | ---------------------------------------------------------------------------------------------------------- |
    | Parakeet v3 | 466 MB | [parakeet-tdt-0.6b-v3-coreml.tar.gz](https://assets.vowen.ai/models/v2/parakeet-tdt-0.6b-v3-coreml.tar.gz) |
    | Parakeet v2 | 451 MB | [parakeet-tdt-0.6b-v2-coreml.tar.gz](https://assets.vowen.ai/models/v2/parakeet-tdt-0.6b-v2-coreml.tar.gz) |
  </Tab>
</Tabs>

## Step 3 — Place the Files

### Whisper (.bin files)

Move the downloaded `.bin` file directly into the `models` folder — do not rename it. For example:

```
C:\Users\<you>\AppData\Roaming\Vowen\models\ggml-small.bin
```

### Parakeet (.tar.gz archives)

Extract the archive into the `models` folder.

<Tabs>
  <Tab title="Windows">
    Open PowerShell and run (adjust the filename to the one you downloaded):

    ```powershell theme={null}
    cd $env:APPDATA\Vowen\models
    tar -xzf $env:USERPROFILE\Downloads\parakeet-tdt-0.6b-v3-int8.tar.gz
    ```

    You can also use 7-Zip or WinRAR — extract twice if needed (`.tar.gz` → `.tar` → folder).

    The end result must be a folder with the exact archive name (e.g. `parakeet-tdt-0.6b-v3-int8`), containing `.onnx` files directly inside it — not nested inside another folder.
  </Tab>

  <Tab title="macOS">
    Open Terminal and run (adjust the filename to the one you downloaded):

    ```bash theme={null}
    cd ~/Library/Application\ Support/Vowen/models
    tar -xzf ~/Downloads/parakeet-tdt-0.6b-v3-coreml.tar.gz
    ```

    The end result must be a folder with the exact archive name (e.g. `parakeet-tdt-0.6b-v3-coreml`), containing `.mlmodelc` folders directly inside it.
  </Tab>
</Tabs>

## Step 4 — Restart Vowen

Start Vowen again and go to **Settings > Models**. The model should now show as downloaded. Select it and try a dictation.

## Troubleshooting

**Model not detected after restart**

* Check the filename matches exactly (e.g. `ggml-small.bin`, not `ggml-small (1).bin` — browsers add "(1)" if you downloaded the file twice).
* Vowen validates file size, so a partially downloaded file won't be detected. Compare your file's size against the table above and re-download if it's smaller.

**Leftover files in the models folder**

* Files ending in `.part` or `.partial`, and folders ending in `.extracting`, are failed in-app downloads. It's safe to delete them.

**Parakeet shows as not installed**

* Open the extracted folder and confirm the model files (`.onnx` on Windows, `.mlmodelc` on macOS) are directly inside it. If extraction created a folder inside a folder, move the inner one up one level.

## For Network Administrators

To make in-app downloads work directly, the following domains need to be reachable from the user's machine:

* `huggingface.co` — Whisper models
* `cdn-lfs.huggingface.co` and `cdn-lfs-us-1.huggingface.co` — Hugging Face redirects downloads to these CDN hosts
* `assets.vowen.ai` — Parakeet and other Vowen-hosted models

<Note>
  Allowlisting the domains may not be enough if the network performs SSL inspection (certificate replacement) — that is what causes the "self signed certificate in certificate chain" error. These domains need to be exempted from SSL inspection/decryption, not just allowed.
</Note>

## Still Stuck?

Join our [Discord community](https://discord.gg/vowen) or email us — send a screenshot of the error and the contents of your models folder, and we'll help you sort it out.