#OpenSourceDiscovery 83: Coqui TTS
A deep learning toolkit for Text-to-Speech
Today I discovered…
Coqui TTS
Clone voices and generate speech from text with pertained models in +1100 languages
💖 What I like about Coqui:
Quick and lightweight installation
Decent text-to-speech output
Supports multiple TTS models and allows fine-tuning
👎 What I dislike about Coqui:
Cloned voice had some features of the source voice but still doesn't feel like a cloned voice. This was when used XTTS model, haven't used any other model.
Underlying XTTS model is not open-source
⭐ Ratings and metrics
Based on my experience, I would rate this project as following
Production readiness: 7/10
Docs rating: 7/10
Time to POC(proof of concept): 1 week
Author: Eren Gölge @erogol and Coqui team
Demo | Source
🛡 License: MPL-2.0
Tech Stack: Python, Jupyter Notebook, Shell🗣️ What people say about Coqui around the web
You can also discuss in response to this post on Substack
If you discovered an interesting Open-Source project and want me to feature it in the newsletter, get in touch via the form above. To support this newsletter and Open-Source authors, follow #OpenSourceDiscovery on LinkedIn and Twitter