As open speech recognition, translation, and TTS models continue to improve, it feels increasingly possible to build communication tools that run on infrastructure users actually control.

That's one of the ideas behind PolyTalk, an open-source translation platform we're building.

Privacy, ownership, and transparency may soon matter as much as model quality.

Do you think communication tools like translation, transcription, and speech interfaces will eventually move back toward local and self-hosted deployments?

GitHub: https://github.com/PolyTalkIO/polytalk

top 4 comments

sorted by: hot top controversial new old

[–] CrypticCoffee@lemmy.ml 4 points 3 days ago* (last edited 3 days ago)

Got a complaint that this is an ad. We don't really have a rule against that and I'd assume in an open source community, sharing repos and projects is part of it. There is a repo link.

I'll allow it. Discuss as you will.

[–] thingsiplay@lemmy.ml 6 points 3 days ago (1 children)

Post title is clickbait. It should contain the name of the program. Really this is not YouTube... Also why is every sentence its own paragraph?

Sorry for being this negative, nothing against the project, just against this post that looks like something out of a marketing team to me.

[–] PolyTalk_BizzAppDev@lemmy.world 2 points 2 days ago

Fair point. I was trying to focus on the broader topic rather than lead with the project, but I can see why that might come across as marketing-style framing.

[–] anamethatisnt@sopuli.xyz 6 points 3 days ago

There are ton of great selfhosted tools for tts and similar interfaces.
I used https://github.com/resemble-ai/chatterbox to make my own voice read my epubs, albeit with an american accent which I definitely don't have in real life. It was close enough to put the voice in the uncanny valley according to my wife.

I think most end users will go for a cloud app or website for their needs though, playing around with self-hosting isn't for everyone.