domesticatedviking/TextyMcSpeechy
Easily create Piper text-to-speech models in any voice. Make a text-to-speech model with your own voice recordings, or use thousands of RVC voices. Works offline on a Raspberry pi. Rapidly record custom datasets for any metadata.csv file and listen to your model as it is training.
This tool helps you create personalized text-to-speech voices for various applications, even running offline on devices like a Raspberry Pi. You provide your own audio recordings or use existing voice datasets, and it outputs a custom voice model. This is perfect for hobbyists, smart home enthusiasts, or anyone wanting to add unique vocal flair to their projects.
631 stars. No commits in the last 6 months.
Use this if you want to generate a unique text-to-speech voice from scratch or by leveraging existing voice recordings for use in your smart home or other projects.
Not ideal if you need a quick, ready-to-use voice without any customization, or if you don't have access to a dedicated NVIDIA GPU for training.
Stars
631
Forks
34
Language
Shell
License
MIT
Category
Last pushed
Apr 07, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/domesticatedviking/TextyMcSpeechy"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
davidacm/NVDA-IBMTTS-Driver
This project is aimed at developing and maintaining the NVDA IBMTTS driver. IBMTTS is a...
marty1885/paroli
Streaming TTS based on Piper with optional RK3588 NPU support
IhorShevchuk/piper-app
The original Piper, now on iOS and macOS
artibex/piper-http
Creates a docker image that runs the piper http service
ayutaz/piper-plus
Multilingual neural TTS (6 languages: JA/EN/ZH/ES/FR/PT) with VITS architecture. 571 speakers,...