Ancestors

Toot

Written by boredsquirrel on 2024-10-08 at 21:45

Opensource modern TTS engines for Android are now available!

https://slrpnk.net/post/14072937

=> More informations about this toot | More toots from boredsquirrel@slrpnk.net

Descendants

Written by macattack@lemmy.world on 2024-10-08 at 23:11

Might want to link to the official page for a bit more context

=> More informations about this toot | More toots from macattack@lemmy.world

Written by iturnedintoanewt@lemm.ee on 2024-10-09 at 02:44

For context really, because figuring out the android install there ain’t a straight thing.

I’ve been using these TTS for a few months now, and I’m seriously impressed with its quality. I always find funny when it tells me to TURN LAFT ON THE NEXT ROUND… ABOUT, but that’s a really minor nit picking, overall audio quality is amazing.

=> More informations about this toot | More toots from iturnedintoanewt@lemm.ee

Written by macattack@lemmy.world on 2024-10-10 at 06:49

Just to clarify, this is standalone and doesn’t need a local LLM or anything yeah? Also, any tips on tutorials for the install process?

=> More informations about this toot | More toots from macattack@lemmy.world

Written by iturnedintoanewt@lemm.ee on 2024-10-10 at 10:06

Yup, standalone and doesn’t require anything else, no connectivity whatsoever. It runs local.

=> More informations about this toot | More toots from iturnedintoanewt@lemm.ee

Written by Sir_Kevin@lemmy.dbzer0.com on 2024-10-09 at 05:38

Can I install it via F-Droid?

=> More informations about this toot | More toots from Sir_Kevin@lemmy.dbzer0.com

Written by boredsquirrel on 2024-10-09 at 06:32

It is FOSS, and the build instructions are here

k2-fsa.github.io/sherpa/…/build-sherpa-onnx.html

Those guys are incredibly active, look at this!

k2-fsa.github.io/sherpa/onnx/index.html

(And no, not on F-Droid, if you look at the crazy amount of packages that makes sense)

=> More informations about this toot | More toots from boredsquirrel@slrpnk.net

Written by Swedneck@discuss.tchncs.de on 2024-10-09 at 17:38

that stupid huge amount of packages is honestly a pretty big UX issue, at least personally that just makes me chuckle at their optimism and close the page as every bit of energy i had vaporizes from the thought of figuring out what to download.

=> More informations about this toot | More toots from Swedneck@discuss.tchncs.de

Written by boredsquirrel on 2024-10-09 at 19:14

Just scroll down until the page is fully loaded and use the search function.

=> More informations about this toot | More toots from boredsquirrel@slrpnk.net

Written by PlexSheep@infosec.pub on 2024-10-12 at 11:04

Yeah but search for what even?

=> More informations about this toot | More toots from PlexSheep@infosec.pub

Written by boredsquirrel on 2024-10-12 at 11:28

your language abbreviation like “de” or “en”

=> More informations about this toot | More toots from boredsquirrel@slrpnk.net

Written by Lemongrab on 2024-10-09 at 07:50

github.com/k2-fsa/sherpa-onnx

=> More informations about this toot | More toots from Lemongrab@lemmy.one

Written by BarHocker@discuss.tchncs.de on 2024-10-09 at 12:13

I there a way to install multiple languages? I, for example, would like to install both English and German so that I can switch between them depending on the language of the text.

=> More informations about this toot | More toots from BarHocker@discuss.tchncs.de

Written by Rogers@lemmy.ml on 2024-10-09 at 19:33

This is amazing! If you are looking for US EN and use a phone with arm64 I can recommend sherpa-onnx-1.10.27-arm64-v8a-en-tts-vits-piper-en_US-kristin-medium and sherpa-onnx-1.10.27-arm64-v8a-en-tts-vits-piper-en_US-norman-medium

=> More informations about this toot | More toots from Rogers@lemmy.ml

Written by boredsquirrel on 2024-10-09 at 20:01

These names are a joke hahaha

=> More informations about this toot | More toots from boredsquirrel@slrpnk.net

Written by Semperverus on 2024-10-09 at 21:06

You are clearly not the target audience then. There is a lot of extremely useful info in those model names.

=> More informations about this toot | More toots from semperverus@lemmy.world

Written by boredsquirrel on 2024-10-10 at 07:23

Yes of course :) I use sherpa-onnx-1.10.26-arm64-v8a-de-tts-engine-vits-piper-de_DE-thorsten-medium and there is nothing irrelevant in that name.

Still after another commenter wrote how overwhelmed they are with that INSANE download page, I felt that when you dropped those 2 names

=> More informations about this toot | More toots from boredsquirrel@slrpnk.net

Written by Rogers@lemmy.ml on 2024-10-09 at 21:47

Yeah IMO they need an app that can download/manage models directly

=> More informations about this toot | More toots from Rogers@lemmy.ml

Written by boredsquirrel on 2024-10-10 at 07:21

That would then require running code from memory, which needs to be enabled in recent GrapheneOS. But all fine, they should absolutely do that as they obviously do that currently but during compilation.

Client app + wizard to select language and model type + downloaded model

=> More informations about this toot | More toots from boredsquirrel@slrpnk.net

Written by boredsquirrel on 2024-10-10 at 07:24

Yes they have 3 types of client apps

=> More informations about this toot | More toots from boredsquirrel@slrpnk.net

Written by justtobbi@feddit.org on 2024-10-09 at 21:07

How do I apply these voices, so apps use it?

=> More informations about this toot | More toots from justtobbi@feddit.org

Written by justtobbi@feddit.org on 2024-10-10 at 07:07

Go into Settings -> Accessability -> Speech (at the very bottom; at least on Android 13) and then TTS :) hope that helps

=> More informations about this toot | More toots from justtobbi@feddit.org

Written by boredsquirrel on 2024-10-10 at 07:24

They have 3 types of clients, only one works as an Android TTS engine, the others are useless.

=> More informations about this toot | More toots from boredsquirrel@slrpnk.net

Written by justtobbi@feddit.org on 2024-10-10 at 09:07

I downloaded the thorsten medium and wondered, what the difference to thorsten high would be?

=> More informations about this toot | More toots from justtobbi@feddit.org

Written by Teppichbrand@feddit.org on 2024-10-10 at 11:10

You can listen to them here

=> More informations about this toot | More toots from Teppichbrand@feddit.org

Written by boredsquirrel on 2024-10-10 at 17:39

Thorsten high is silly haha. Emotional is also not meant for TTS more for research I think.

I think thorsten made the only good model in German, I really want to make my own one! Or get some famous people on board?

=> More informations about this toot | More toots from boredsquirrel@slrpnk.net

Written by macattack@lemmy.world on 2024-10-10 at 07:34

To those late to the party, you can sample voices here so that you’re not in a crapshoot:

rhasspy.github.io/piper-samples/

=> More informations about this toot | More toots from macattack@lemmy.world

Written by boredsquirrel on 2024-10-10 at 17:39

Nice, thanks!

=> More informations about this toot | More toots from boredsquirrel@slrpnk.net

Written by Teppichbrand@feddit.org on 2024-10-10 at 10:49

eSpeak is a damn good conversation starter. If I fire up OsmAnd and some german robot with a dutch accent (or is it Kölsch?!) starts giving me directions noone ever not commented on it. Downloading Thorsten Medium right now.

=> More informations about this toot | More toots from Teppichbrand@feddit.org