lucasnewman/e2-tts-mlx

Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in MLX

33
/ 100
Emerging

This project helps developers and researchers create custom text-to-speech (TTS) systems. It takes written text and a reference audio sample, and outputs generated speech that matches the voice from the reference. This tool is for machine learning engineers, AI researchers, and audio developers working on speech synthesis applications.

No commits in the last 6 months.

Use this if you need to quickly train a new text-to-speech model that can adapt to different voices from short audio samples, without complex data alignment.

Not ideal if you're an end-user looking for a ready-to-use text-to-speech application; this is a development tool for building such systems.

speech-synthesis text-to-speech zero-shot-learning machine-learning-development audio-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

21

Forks

3

Language

Python

License

MIT

Last pushed

Oct 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/lucasnewman/e2-tts-mlx"

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