I would be plus if it has a simple CLI or GUI.
speechnote by kde
I think Bark from Suno is quite good : https://github.com/suno-ai/bark
F5-TTS. Only needs 15 seconds of reference audio and you’re good to go.
I use piper TTS. Probably not as good as the fancy AI APIs, but it’s all local and runs from command line and is good enough for my purposes. YMMV.
For setting up Piper TTS on Desktop Linux: https://pied.mikeasoft.com/
I was disappointed with this at first, until I loaded the “Cori” voiceset. It outshines the others
The ones I liked the most was Kusal and Lessac.
Depends on your setup, but generally I recommend: https://github.com/SYSTRAN/faster-whisper
If you have an available GPU for processing it’s insanely quick and better than OpenAI’s whisper.
this is speech-to-text! OP is looking for text-to-speech.
There’s zonos, and I heard of another one called GPTsovit or something like that, but I haven’t tried that one. Zonos is pretty easy to setup and run though. Another one is Kokoro, search for Kokoro TTS to find it on google.
RHVoice works well enough for me. https://f-droid.org/packages/com.github.olga_yakovleva.rhvoice.android/
Maybe but if you can’t use Google you won’t be able to use them either.
Or even the Lemmy search, because it’s been discussed here before.
