LEMAS-Project/LEMAS-TTS

LEMAS‑TTS is a multilingual zero‑shot text‑to‑speech system, supporting 10 languages: Chinese English Spanish Russian French German Italian Portuguese Indonesian Vietnamese

35
/ 100
Emerging

This tool helps content creators, educators, or anyone needing to convert text into spoken audio in multiple languages without needing a recording studio. You input text in one of ten supported languages (like English, Spanish, or Chinese), and it outputs realistic-sounding speech audio. It also allows for editing existing speech recordings by modifying specific regions.

Use this if you need high-quality, natural-sounding voiceovers or narration for videos, e-learning materials, or audio content in various languages without professional voice actors.

Not ideal if you require a voice in a language not listed among the ten supported, or if you need to generate highly emotional or nuanced speech beyond standard narration.

voice-synthesis content-creation e-learning multilingual-communication audio-editing
No License No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 5 / 25
Community 11 / 25

How are scores calculated?

Stars

92

Forks

8

Language

Python

License

Last pushed

Jan 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/LEMAS-Project/LEMAS-TTS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.