Modern TTS Engine

I find there is a space for improvement for TTS Engines available on F-Droid.

It would be ideal to make it possible to install MycroftAI Mimic3 GitHub - MycroftAI/mimic3: A fast local neural text to speech engine for Mycroft or Piper GitHub - rhasspy/piper: A fast, local neural text to speech system as the engine. I have been enjoying Mimic3 on desktop for months and it’s great. But on the phone, it doesn’t install even on Termux. I would love to work on that, but am curious how many people would want to fund such development.

Please post here or reach out privately if you want to see it happen and willing to chime in with funding.

1 Like

I use RHVoice for Organic maps and that’s all it’s good for, the quality is very poor. A Better TTS for an e-book reader would definitely be useful.

A good open TTS is really missing.

There is a STT though: https://alphacephei.com/vosk/

I just found this project based on piper.

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

how to Build sherpa-onnx for Android — sherpa 1.3 documentation

or Build sherpa-ncnn for Android — sherpa 1.3 documentation

and Custom build | onnxruntime

and etc

TTS with emotions This is very cool.

GitHub - suno-ai/bark: 🔊 Text-Prompted Generative Audio Model

GitHub - coqui-ai/TTS: 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

GitHub - mozilla/TTS: 🤖 Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)