lucasnewman/nanospeech

A simple, hackable text-to-speech system in PyTorch and MLX

52
/ 100
Established

This project helps researchers and developers explore and modify text-to-speech technology. It takes plain text and optionally a speech sample, and outputs generated speech in various voices, or a voice matching the sample. This is for machine learning researchers, audio engineers, or anyone wanting to customize or understand text-to-speech systems.

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

Use this if you are a researcher or developer looking for a straightforward, adaptable text-to-speech system to experiment with or build upon.

Not ideal if you need a production-ready, highly accurate text-to-speech system for commercial applications without further training.

speech-synthesis audio-generation voice-cloning machine-learning-research digital-audio-processing
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 15 / 25

How are scores calculated?

Stars

186

Forks

21

Language

Python

License

MIT

Last pushed

Aug 03, 2025

Commits (30d)

0

Dependencies

13

Get this data via API

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

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