Text To Speech and Voice Cloning

 There are seemingly a million Text to Speech and voice clone things being released. I'm going to note what I find, or my buddy Nate sends me here. (Also some other interesting tools will be noted too ;)). I'm noting the date of their first github commit on the repository too.

TTS (Text to Speech)

TinyTTS: https://github.com/tronghieuit/tiny-tts.git

KittenTTS: https://github.com/KittenML/KittenTTS 8/4/2025

LuxTTS: https://github.com/ysharma3501/LuxTTS 1/23/2026

Qwen3TTS: https://github.com/QwenLM/Qwen3-TTS 1/22/2026 

PersonaPlex: https://research.nvidia.com/labs/adlr/personaplex/ 1/15/2026 

Chroma: https://github.com/FlashLabs-AI-Corp/FlashLabs-Chroma 11/13/2025

NeuTTS: https://github.com/neuphonic/neutts 10/2/2025 

Inworld TTS: https://github.com/inworld-ai/tts 7/29/2025

Pocket TTS: https://github.com/kyutai-labs/pocket-tts

Soprano TTS: https://github.com/ekwek1/soprano 

Sopro TTS: https://github.com/samuel-vitorino/sopro

VibeVoice: https://github.com/microsoft/VibeVoice

Liquid Audio: https://github.com/Liquid4All/liquid-audio

VoxTream TTS: https://github.com/herimor/voxtream 

Mimo Audio: https://github.com/XiaomiMiMo/MiMo-Audio 

VoxCPM TTS;  https://github.com/OpenBMB/VoxCPM

 

... There are plenty more, I'll update as I have time. 

STT (Speech to Text)

Whisper 

GLM ASR Nano: https://github.com/zai-org/GLM-ASR

Moonshine: https://github.com/moonshine-ai/moonshine

Tools:

Qwen3-Audiobook-Converter: https://github.com/WhiskeyCoder/Qwen3-Audiobook-Converter

Meta Segment Anything Model Audio: (No link, I have facebook/meta blocked at my house, and don't feel like turning off my blocker).

In browser TTS:

https://github.com/MbBrainz/ttslab 

 

 * Note I got hit with a rate limit checking the commit history of the repos soooo dunno when I'll have dates on some of these.

Latest Projects

I received a Raspberry Pi for fathers day, so I've played around a little with it. So far I've built two projects, and they're located at github.

This is a wrapper to download a mRSS feed and then play it in a random order on your Raspberry Pi
https://github.com/onaclov2000/omxrssplayer

This is a Text to Speech wrapper, that uses google to do the translating, it could really do some improvement, by counting the letters, then splitting on or before the 100th letter (space).
https://github.com/onaclov2000/pytts

I'm working on using the code from this link:
https://github.com/raspberrypi/firmware/tree/master/opt/vc/src/hello_pi/hello_font
to try to overlay a news feed of sorts over the OMXrssplayer (wrapper) app I wrote.

I would like to keep working on the pytts, and get a pystt (speech to text), and then have it listen to my voice and do things (kinda like Jarvis from Iron Man :) )

I thought it would be fun to setup a chatbot and then connect all three, so I say something, it relays it to the chatbot, which responds, then it converts that to speech, so it can talk to you!

Anywho if you like it, and want to start building up components that would be cool, let me know, I would love to build it to work with Wolfram Alpha too, but even more I'd like for it to have a learning algorithm so it can be taught, and/or learn. (I like AI, but don't know much about it yet).