CSTR-Edinburgh/magphase

MagPhase Vocoder: Speech analysis/synthesis system for TTS and related applications.

45
/ 100
Emerging

This system helps improve the quality and naturalness of synthetic speech for text-to-speech (TTS) and voice conversion applications. It takes raw speech recordings as input, extracts detailed sound characteristics, and then uses these to generate more realistic-sounding synthesized voices. This is useful for speech scientists, researchers, and developers working on advanced speech synthesis models.

No commits in the last 6 months.

Use this if you are developing statistical parametric speech synthesis systems and need a robust way to analyze and synthesize speech waveforms with improved sound quality, especially regarding the naturalness of phase spectra.

Not ideal if you are looking for a simple, off-the-shelf TTS application for end-users, or if you require out-of-the-box support for macOS or Python 3 without any modifications.

speech-synthesis text-to-speech voice-conversion audio-engineering speech-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

80

Forks

31

Language

Python

License

Apache-2.0

Last pushed

Oct 14, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/CSTR-Edinburgh/magphase"

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