hathibelagal-dev/str2speech

An easy-to-use library and command-line tool for TTS

32
/ 100
Emerging

Supports multiple transformer-based TTS models (Kokoro, MegaTTS3, Spark-TTS, SpeechT5, etc.) with voice cloning capabilities via command-line or Python API. Leverages Hugging Face model hub integration and works on CPU or GPU, with espeak-ng for phoneme processing. Features voice preset selection, adjustable speech speed (Kokoro), and multilingual support across models.

Used by 1 other package. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 2 / 25
Adoption 7 / 25
Maturity 18 / 25
Community 5 / 25

How are scores calculated?

Stars

15

Forks

1

Language

Python

License

GPL-3.0

Last pushed

May 03, 2025

Commits (30d)

0

Dependencies

28

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/hathibelagal-dev/str2speech"

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