Opensource modern TTS engines for Android are now available!

https://k2-fsa.github.io/sherpa/onnx/tts/apk-engine.html

I just found this.

APKs for TTS engines

Main page

This is huge!

As a german, I use thorsten medium as he simply made the best dataset.

Mixing english with german, speaking numbers, single letters, pausing without a "." but just a linebreak, all those can be essential.

And... it is nearly perfect! And all local!

This is crazy!

eSpeak can finally go to rest!

195 points · 40 comments · view on lemmy.world

40 Comments

macattack@lemmy.world · 32 pts · 1y (3 replies)

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

iturnedintoanewt@lemm.ee · 6 pts · 1y (2 replies)
[ removed ]
macattack@lemmy.world · 1 pts · 1y (1 reply)

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?

Edit: Nevermind, I realize it's install and use

iturnedintoanewt@lemm.ee · 2 pts · 1y
[ removed ]
macattack@lemmy.world · 10 pts · 1y (1 reply)

To those late to the party, you can sample the piper-related voices here so that you're not in a crapshoot: https://rhasspy.github.io/piper-samples/

boredsquirrel@slrpnk.net · 2 pts · 1y

Nice, thanks!

Lemongrab@lemmy.one · 8 pts · 1y
BarHocker@discuss.tchncs.de · 7 pts · 1y

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.

Sir_Kevin@lemmy.dbzer0.com · 7 pts · 1y (5 replies)

Can I install it via F-Droid?

boredsquirrel@slrpnk.net · 4 pts · 1y (4 replies)

It is FOSS, and the build instructions are here

https://k2-fsa.github.io/sherpa/onnx/android/build-sherpa-onnx.html

Those guys are incredibly active, look at this!

https://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)

Swedneck@discuss.tchncs.de · 6 pts · 1y (3 replies)

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.

boredsquirrel@slrpnk.net · 0 pts · 1y (2 replies)

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

PlexSheep@infosec.pub · 1 pts · 1y (1 reply)

Yeah but search for what even?

boredsquirrel@slrpnk.net · 1 pts · 1y

your language abbreviation like "de" or "en"

Rogers@lemmy.ml · 6 pts · 1y (6 replies)

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.

Edit: I don't seem to be able to get the engine to show up as a tts engine but it works well within the tts app itself. Hopefully I'll find a fix I've been searching for a good tts engine for android eBook apps.

Edit 2. Fixed I mistakenly downloaded the standalone version from https://k2-fsa.github.io/sherpa/onnx/tts/apk.html instead of https://k2-fsa.github.io/sherpa/onnx/tts/apk-engine.html

boredsquirrel@slrpnk.net · 2 pts · 1y (4 replies)

These names are a joke hahaha

Rogers@lemmy.ml · 5 pts · 1y (1 reply)

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

boredsquirrel@slrpnk.net · 1 pts · 1y

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

semperverus@lemmy.world · 1 pts · 1y (1 reply)

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

boredsquirrel@slrpnk.net · 1 pts · 1y

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

boredsquirrel@slrpnk.net · 1 pts · 1y

Yes they have 3 types of client apps

Teppichbrand@feddit.org · 4 pts · 1y (1 reply)

eSpeak is a damn good conversation starter. If I fire up my 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.

boredsquirrel@slrpnk.net · 1 pts · 1y

Hahaha yes it is.

xlash123@sh.itjust.works · 4 pts · 1y (1 reply)

Lmao, there's a GLaDOS voice. I'm taking that

boredsquirrel@slrpnk.net · 1 pts · 1y

Whats that? Mind to share an audio file?

Eyck_of_denesle@lemmy.zip · 1 pts · 1y (10 replies)

How do I install it, I don't understand

boredsquirrel@slrpnk.net · 1 pts · 1y (9 replies)

Search, click on link, install, open app, open android settings, search for tts, enable the app as tts

Eyck_of_denesle@lemmy.zip · 2 pts · 1y (6 replies)
boredsquirrel@slrpnk.net · 1 pts · 1y (5 replies)

Uhm that is the site I have linked

Trust me, I checked 3 times and that tiny link isnt making it easier XD

Eyck_of_denesle@lemmy.zip · 1 pts · 1y (4 replies)

You linked the download apk directly, not the index with all the apk's.

Edited my previous reply for you to see the url better

boredsquirrel@slrpnk.net · 1 pts · 1y (3 replies)

No the main link in the post is exactly the same.

Eyck_of_denesle@lemmy.zip · 1 pts · 1y (2 replies)

You edited it. Lmao why you messing with me.

boredsquirrel@slrpnk.net · 1 pts · 1y

I added the same link also to the text so that you can find it there too.

Click on either of these links, they are the same

Eyck_of_denesle@lemmy.zip · 1 pts · 1y (1 reply)

I don't know what to search. I downloaded a package from github releases android.bz2but it doesn't have any apk.

boredsquirrel@slrpnk.net · 1 pts · 1y

Yeah well you need a .apk XD

just search for

  • your language
  • your android architecture (normally modern phones use arm64 or aarch64 or arm v8a
  • your preferred model, or just try out all

Example

https://huggingface.co/csukuangfj/sherpa-onnx-apk/resolve/main/tts-engine-new/1.10.29/sherpa-onnx-1.10.29-arm64-v8a-de-tts-engine-vits-piper-de_DE-thorsten-medium.apk

justtobbi@feddit.org · 1 pts · 1y (5 replies)

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

justtobbi@feddit.org · 2 pts · 1y (4 replies)

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

boredsquirrel@slrpnk.net · 2 pts · 1y (3 replies)

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

justtobbi@feddit.org · 2 pts · 1y (2 replies)

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

Teppichbrand@feddit.org · 2 pts · 1y

You can listen to them here

boredsquirrel@slrpnk.net · 1 pts · 1y

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?