wannaphong/ttsmms

TTS with The Massively Multilingual Speech (MMS) project

60
/ 100
Established

Wraps Meta's MMS VITS models to enable text-to-speech synthesis across 1,107 languages through a simple Python API with automatic model downloading and audio generation. Built on the VITS vocoder architecture, it provides straightforward synthesis methods that return either NumPy arrays or write directly to WAV files at 16kHz sampling rate. Integrates with the fairseq MMS project's pre-trained multilingual models, requiring only language codes to download and instantiate language-specific TTS engines.

235 stars and 310 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 16 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

235

Forks

38

Language

Python

License

MIT

Last pushed

Jul 12, 2024

Monthly downloads

310

Commits (30d)

0

Dependencies

9

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/wannaphong/ttsmms"

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