🚀 Feature Request

We should be able to click or select a word in the parsed text and then have Audemic start reading from that word. As it is, as far as I can tell, we can only begin reading from a section or by moving the reading bar and guessing to which word it corresponds. Being able to precisely tell Audemic from which word to start readi...

We occasionally have to travel for work and come across areas with poor network coverage. A feature that allows you to read a paper offline, or at the very least save the audio and paper sections for later use, would be extremely useful.

In the Voice Dream Reader app, you can select a mispronounced word, type in the correct pronunciation, hit a play button to check how what you typed is pronounced by the reader, and then save that pronunciation. This would be a useful feature in Audemic.

I have an entire folder with papers that I need uploaded, and by not being able to upload it all at once, it gets very tedious and makes my premium subscription not worth it... Also I have very long papers (>30 pages) and thesis papers (>100 pages) I need read but can't upload it.

When you change the speed in a specific paper and then you play another different paper, it resets the speed to normal again. The idea with this will be to set a speed as default for all your papers.

Greek letters are not recognized by Audemic NLP, so they are not read aloud. It’s important to have these read aloud because they are often part of terminology in scientific papers.

I think there should be option to turn off auto read of complete references!

It is good that Audemic skips Mathematical Formulae instead of just saying the characters, but It is missing important information. It would be great to add support for reading mathematical formulas.

Replace abbreviations with the original, such as instead of HPC says High-Performance Computing. Assuming the original text and abbreviation defined in the paper.

It might be nice to organize masses of papers (like form Zotero) into a folder system (i.e., being able to add folders within folders). For instance, I have a Teams Literature base, but would like to had smaller folders within for specific topics related.

There should be an option specific to each paper that allows us to select whether to read what is inside parenthesis or not (current default). In some cases, what is inside parenthesis is vital, but currently we cannot use audemic on those papers because that content will be skipped.

If I add a highlight to a board by mistake, there is no way to remove or change it. There is also no way to edit the board (i.e., its name, contents) or even delete it if no longer desired.

Read the section titles aloud. Currently it just moves between different sections without telling you it's in the introduction/lit review/results/discussion/conclusion etc. Just say the section title at the start of the recording

.

It would be awesome if it was possible to use the audemic listening while looking at the uploaded pdf. Easier to get a sense of what is happening in the paper and how it is structured then.

When listening to a paper, it would be great if I could easily pause, look at the figure(s) in an image view that supports the normal pan/zoom gestures on my phone, and then resume listening. Currently I need to leave audemic to look at figures.

Would be super useful to be able to move around and rearrange highlights on boards. I use it to help me organize research for project presentations and this would help people who are visual learners to put together the narrative that they are presenting more cohesively rather than feeling as if I am just looking at a pool of ...

It would be nice to have some settings for automatic order of reading. For instance, I typically skip abstract, read intro, skim methods, skim results then read discussion. I recognize that skimming isn’t a option but perhaps a customizable auto priority reading order where i could set it to naturally go straight into the in...

Same can be said for in depth results especially related to figures or tables. When I am listening often I am not looking directly at the table so the descriptions are meaningless. Likewise what takes 5-10 min for machine to read I can understand (assuming well designed figures) in a matter of seconds.

Specifically for for computer science research papers.