Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Web Interface #15

Open
YaibaToKen opened this issue Nov 13, 2023 · 8 comments
Open

Web Interface #15

YaibaToKen opened this issue Nov 13, 2023 · 8 comments
Labels
enhancement New feature or request

Comments

@YaibaToKen
Copy link

Would it be a big ask if we could get (at some point) a web interface, with Readarr/Calibre integration (as well as Audiobook platforms) so we could even configure automated conversions based on Readarr tags or libraries? Bonus points if we could then have it notify a Readarr instance (or even a different audiobook app) that there's a new audio book for it to scan.

@p0n1 p0n1 added the enhancement New feature or request label Nov 14, 2023
@p0n1
Copy link
Owner

p0n1 commented Nov 14, 2023

I agree that it will be nice to have a webui so more users could use this tool easily. It's definitely on the radar. For Readarr/Calibre, I have never used them. Will look into them!

@Bryksin
Copy link
Collaborator

Bryksin commented Nov 23, 2023

Oh, I would definitely support that and will help with the code!
Let's make this little tool to conquer the world :D

On the other side, I feel bad, that if this web service became popular, imagine how many voice-over actors would stay out of jobs?
Considering that some AI can imitate any voice... so far we are limited to TTS models and their voices, but I guess nothing stopping us from parsing TTS voice through some other AI engine to alter that voice to some celebrity :) ahahha
it would definitely increase the cost, but you will have your favourite book voiced by your favourite actor :)

@p0n1
Copy link
Owner

p0n1 commented Nov 24, 2023

I don't have much knowledge about the voice acting industry, but I believe that many professions around the world will need to be repositioned in the coming years due to the rapid development of AI.

BTW, a friend is playing with gradio to see if it suits for this project.

@marchowardbegins
Copy link

A gradio interface would be superb. I definitely agree with @p0n1 in that this could seriously disrupt some professions. I've created 2 audiobooks for far for personal use and it was a mind-blowing experience. Why pay Amazon/Audible $30/audiobook when you could TTS your own for a few bucks in API credits? I have a friend who recently published a book but no audiobook as he was disappointed in the large profit share he would need to pay Amazon not to mention the hours of professional recording and studio editing. He'd rather sell the audiobook directly from his site (although it may sacrifice distribution initially). A gradio interface would make this much more accessible--I could see it as a SaaS product or API licensed to libraries or enterprises. Anyway just some thoughts since I would totally invest in iterations of this project--so much potential.

@Bryksin
Copy link
Collaborator

Bryksin commented Nov 24, 2023

Im not fully sure why would we need gradio, if we talk about SaaS I would see this as serverless project somewhere in AWS.
@p0n1 I would say we could organise some initial meeting call to discuss general evolution plans to sync up and stay on the same page
As well as organise some chat media where we could communicate directly in PM (Discord server?)
Ill back after 4 days and we could organise something

@dynm
Copy link

dynm commented Nov 24, 2023

#24
Gradio is user-friendly for building applications. I have successfully made it fully independent from the original epub_to_audiobook.py. This was achieved by constructing the appropriate arguments and spawning a subprocess to convert the eBook into an audiobook.

@p0n1
Copy link
Owner

p0n1 commented Nov 24, 2023

I would say we could organise some initial meeting call to discuss general evolution plans to sync up and stay on the same page As well as organise some chat media where we could communicate directly in PM (Discord server?) Ill back after 4 days and we could organise something

That would be a lot of fun. I just created a simple discord server for random talk. @Bryksin @marchowardbegins @dynm and anyone else. Feel free to join with this link https://discord.gg/pgp2G8zhS7. Maybe we can schedule a meeting call over there.

@Bryksin
Copy link
Collaborator

Bryksin commented Nov 24, 2023

#24 Gradio is user-friendly for building applications. I have successfully made it fully independent from the original epub_to_audiobook.py. This was achieved by constructing the appropriate arguments and spawning a subprocess to convert the eBook into an audiobook.

Oh its awesome though after my PR with huge project refactoring it would require extra work to assemble everything together, maybe its even worth to ask to wait a bit and not bring in new changes and features until PR would be merged

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

5 participants