hcy71o/AutoVocoder

Autovocoder: Fast Waveform Generation from a Learned Speech Representation using Differentiable Digital Signal Processing

42
/ 100
Emerging

This project helps speech researchers and audio engineers quickly generate high-quality speech waveforms. You provide a learned speech representation, and it outputs realistic spoken audio. This is ideal for those working on speech synthesis, voice cloning, or similar audio generation tasks.

No commits in the last 6 months.

Use this if you need to rapidly convert compressed speech information into audible human speech with state-of-the-art efficiency.

Not ideal if you're looking for a complete text-to-speech solution or a tool for general audio editing.

speech-synthesis audio-generation voice-cloning acoustic-modeling digital-signal-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

71

Forks

13

Language

Python

License

Apache-2.0

Last pushed

Dec 02, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/hcy71o/AutoVocoder"

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