Skip to main content
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).
Press Win + R, enter the following, and press Enter:
Inside that folder, open the models folder. If it doesn’t exist, create a new folder named exactly models. The full path looks like:

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

​
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.

​
Step 3 — Place the Files

​
Whisper (.bin files)

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

​
Parakeet (.tar.gz archives)

Extract the archive into the models folder.
Open PowerShell and run (adjust the filename to the one you downloaded):
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.

​
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
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.

​
Still Stuck?

Join our Discord community or email us — send a screenshot of the error and the contents of your models folder, and we’ll help you sort it out.