this post was submitted on 29 May 2025
27 points (100.0% liked)

GrapheneOS [Unofficial]

2685 readers
55 users here now

Welcome to the GrapheneOS (Unofficial) community

This feed is currently only used for announcements and news.

Official support available on our forum and matrix chat rooms

GrapheneOS is a privacy and security focused mobile OS with Android app compatibility.

Links

More Site links

Social Media

This is a community based around the GrapheneOS projects including the hardened Android Open Source Project fork, Auditor, AttestationServer, the hardened malloc implementation and other projects.

founded 4 years ago
MODERATORS
 

We're looking into using https://github.com/k2-fsa/sherpa-onnx to provide built-in text-to-speech and speech-to-text to greatly improve the out-of-the-box accessibility of GrapheneOS for blind users. We already have a screen reader included via our fork of the open source variant of TalkBack.

To have text-to-speech functioning out-of-the-box, we can choose one of the models with open source training code and data as the default to be included within the OS. We wouldn't need to include anything that's not truly open source. It's the only reasonable option we've found.

There are over 100 models for 40 languages. Some research is going to be required to figure out which of the English ones are fully open source (open training data and code) and then which of those works best for basic text-to-speech to have as the default bundled in the OS.

If we had text-to-speech support included in GrapheneOS, we could also provide an automatic captions feature.

We'll need to do a basic review of the code for text-to-speech, speech-to-text, shared code and any other parts we decide to use. We'll need at least a minor fork of it.

We want to stick to a model with open source training code/data for what we bundle, so we're likely not going to be able to use one of the best options by default. Having a tolerable open source model by default with the option to switch to great "open" models seems good enough.

We could use help narrowing down which of the available English models with open training data would be best (least bad) for basic text-to-speech usage including for TalkBack. We could also collect feedback somewhere on which ones people think are best overall across languages.

top 8 comments
sorted by: hot top controversial new old
[–] z3rOR0ne@lemmy.ml 6 points 1 month ago (1 children)

I use SherpaTTS my GrapheneOS phone. It's quite good imho. Glad to hear you're all considering adding this!

[–] swelter_spark@reddthat.com 5 points 1 month ago

I use Sherpa, too, although I don't use Graphene. It's nice.

[–] humble_boatsman@sh.itjust.works 6 points 1 month ago (1 children)

My wife and I were just gripping about this in terms of a visual voice mail.. Havnt looked hard yet but would love to stick to FOSS

[–] KindnessInfinity@lemmy.ml 5 points 1 month ago (1 children)

GOS already supports Visual Voicemail, actually. As long as the phone carrier also supports it.

[–] humble_boatsman@sh.itjust.works 3 points 1 month ago* (last edited 1 month ago) (1 children)

Hmm. Have to look harder for set up ..... Oh. Transcripts on but issue with... Wait recordered by google? Fuck it I hate voicemails anyway

[–] KindnessInfinity@lemmy.ml 1 points 4 weeks ago (1 children)

Where are you getting this?

[–] humble_boatsman@sh.itjust.works 1 points 3 weeks ago* (last edited 3 weeks ago) (1 children)

Phone: settings: voice mail. Toggling visual voice mail pop ups a window that states google and your carrier may keep transcripts. However it is not currently working so I imagine I would have to call the carrier. And as it stats transcripts may be saved I figured not worth the effort.

[–] KindnessInfinity@lemmy.ml 1 points 2 weeks ago

That message is old and so google isn't being used. It's worth calling your carrier though if you want visual voicemail.