Hi everyone. Iām a blind software developer. I built an AI-powered tool to generate audio description.
I see this project as a way to create quick drafts for professionals, or to provide AD for content that would otherwise never get it due to budget constraints-especially in non-English languages, where accessibility is often lacking.
In my opinion, the results turned out quite solid. To let you judge for yourself, here is an example: the animated short Sprite Fright:
https://drive.google.com/file/d/1xLCFIPgO5V-foRXymnTq73Y0A4TmCGA9/view?usp=sharing
Iād really appreciate your feedback! I also want to test the system with other languages. If you'd like to check how it sounds in your native language, let me know in the comments or email me at marina.akenteva@gmail.com-I can run a free 10ā15 minute test on a video you provide.
Comments
link?
Apologies, but how are we meant to test if we don't have a link or some form of thing to actually test it with?
Re: link?
Link' available in the top now.
Clarification about testing
The app itself is currently in development. Right now, I'm interested in feedback on the quality of the audio description itself. You can send me a video, and I will send back the audio description for it.
It works fine.
But what makes it stand out from, for example, vidiscribe:https://viddyscribe.com/dashboard/realtime
Comparing with ViddyScribe
Thanks for pointing that out!
If this project ever turns into a full public app, my plan is to keep the pricing significantly lower.
I wanted to compare the quality with ViddyScribe directly, but as far as I understand, creating standard audio description without pauses requires a paid subscription. If anyone has an example of a video processed with ViddyScribe, Iād be curious to check it out and compare the results with my tool.
without pauses is nice but...
You don't get as much info. it's so interesting that there's at least 3 or so audio description tools now. Yeah i just checked and I need to upgrade to get standard audio description.
I stil like their youtube part though that is a huge win for me but if they're all working on the same backend, I think sonarpad uses google for example, we aren't really getting anything that stands out are we?
I find it a bit strange how you have to contact vidiscribe for their individual plans, oh it's nothing bad just... not how I'd do it.
If you wanted to stand out and have something I'd personally pay for, i think I'd like to write to the video. Like if we take Abby from the last of us, what does she look like, call her Abby and store it in the databass, look up the last of us lore and include that, that kind of thing, I don't know if that's doable just yet with AI.
Re: without pauses is nice but...
not everyone likes pauses in videos though. That is why i don't use vidiscribe
Sonarpad
Hello everyone, I wanted to let you know that Sonarpad does what you are asking for, meaning the audio descriptions, unless explicitly chosen by the user, do not pause the movie and only speak during silences, that is, not over the actors' words.
In addition, it is available for Windows, Mac, iOS, and Android.
Re: Sonarpad
w self-promo here, i haven't used the app yet on my mack, i hav the app, i'll get it all stetup later but should hav some good fun with it
Re: Sonarpad
Edit:I was wrong, read the post below this one to find out more.
I'd just like to point out the AD is paid for. People aren't really at the stage where they can give audio description for free just yet.
Give it another year or maybe even less and we might get there though but for now, yeah , all these apps are paid for.
Brad
Hi Brad, I'd just like to correct one thing. Sonarpad is completely free, and so is the audio description feature.
Of course, you need to set up your own Gemini API key, and the free model isn't as powerful as the paid one. That said, I have users who have managed to audio describe entire TV series, even five or six seasons, using nothing but a free API key.
Yes, I do offer a paid service, but it's really just an extra convenience for people who don't want to deal with setting up Gemini, getting an API key, or the occasional issues and limitations that come with the free tier.
But I want to make one thing very clear: Sonarpad is free, and it will always remain completely free. The paid service is simply an optional extra, not something you need in order to use the app or create audio descriptions.
Re: Brad
ah fair enough. Yeah the app is completely fre, and if you can get the google key working then yeah that's free too.
I made a mistake there. I won't delete it so others can read and learn from this but i'll update that post.
how can I test it with my native language, ?
well, I am Ming from Hong Kong.
I would like to test it.
and through the google drive link. I think it is really cool!