speechnote by kde
this post was submitted on 25 Feb 2025
53 points (100.0% liked)
Open Source
33375 readers
84 users here now
All about open source! Feel free to ask questions, and share news, and interesting stuff!
Useful Links
- Open Source Initiative
- Free Software Foundation
- Electronic Frontier Foundation
- Software Freedom Conservancy
- It's FOSS
- Android FOSS Apps Megathread
Rules
- Posts must be relevant to the open source ideology
- No NSFW content
- No hate speech, bigotry, etc
Related Communities
Community icon from opensource.org, but we are not affiliated with them.
founded 5 years ago
MODERATORS
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/