stefantaubert/en-tts

Command-line interface and Python library for synthesizing English texts into speech.

39
/ 100
Emerging

Supports IPA phoneme-based synthesis with explicit control over stress, duration, and breaks through a text-to-IPA transcription pipeline, leveraging PyTorch 2.0+ for the underlying neural vocoder. Includes a web interface via Gradio, command-line tool, and programmatic Python API for batch processing and audio normalization, with pre-trained models published on Zenodo and integrated with Hugging Face Spaces for cloud deployment.

No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 2 / 25
Adoption 7 / 25
Maturity 18 / 25
Community 12 / 25

How are scores calculated?

Stars

5

Forks

1

Language

Python

License

MIT

Last pushed

Sep 01, 2025

Monthly downloads

14

Commits (30d)

0

Dependencies

16

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/stefantaubert/en-tts"

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