Skip to main content

Auto-learn from corrections + bulk dictionary import

Feature Request

Hi Vowen team,

First off, I really like your project, it's really useful.

I wanted to share a couple of ideas that would make it even more powerful:

1. Auto-learn from manual corrections

When a word gets transcribed incorrectly and I fix it by hand in the text, it would be great if the app noticed that and silently added the correction to my custom dictionary in the background. So the next time I say the same thing, it already knows what I mean - no extra steps.

For example, I often say "DeepL" (the translation tool), and Vowen transcribes it as something like "dipl". If it learned from that first correction, I'd never have to fix it again.

2. Bulk import words via .txt or .csv file

Right now, adding technical or niche vocabulary one word at a time can be pretty tedious. It would be really handy to be able to upload a plain text or CSV file with a list of words to add to the dictionary all at once.

This would be especially useful for people who work in specific fields - for example, developers who regularly say things like MySQL, PHP, Supabase, or prompt engineering terms, or really anyone working in a niche where standard speech recognition tends to struggle. Being able to prepare a word list in advance and import it in one shot would save a lot of time.

Thanks for considering it, and keep up the great work!

Posted by dimezio ·
Status: Completed2 comments

Log in to comment and vote

Comments2

  • Vowen

    Team•

    May 19

    Hey @dimezio , we’ve added both of these features in our latest update v0.4.0. “Auto-learn from manual corrections” is a paid feature. You can purchase our one-time license to use this on upto 3 devices and you get lifetime updates.

  • Nikolai Vysotskyi

    •

    May 18

    Hi there,

    I have a few suggestions regarding the functionality for bulk dictionary import/learning. I believe expanding this feature would significantly improve its utility and usability

    1. Need for Increased Capacity in Dictionary Processing: The current limit of 50 words in the dictionary seems too small. We need a substantial increase in capacity.

      1. Context: I have sufficient processing power on my local machine to handle significantly larger volumes.

      2. Goal: I understand this could potentially be solved using system instructions for LLM models, but since we already have a dictionary feature, this functionality should ideally be built-in.

      3. Requirement: I strongly desire for this feature to work "out of the box," be configurable, and allow users to import hundreds or even thousands of words (e.g., 500 or 1000 words), not just 50.

    2. Reference for Existing Implementation (Wisprflow.ai): I found a similar implementation on wisprflow.ai that might offer insight into how this could be achieved. Please review this implementation; it might provide a useful direction or blueprint for how to build the desired bulk learning capability.

    Thank you for considering these points. I look forward to hearing your thoughts on how we can implement this feature.