Sopro: A 169M parameter real-time TTS model with zero-shot voice cloning (github.com) 6 points by marques576 6mo ago ↗ HN
[–] marques576 6mo ago ↗ Some features:169M parametersStreaming supportZero-shot voice cloning0.25 RTF on CPU, meaning it generates 30 seconds of audio in 7.5 secondsRequires 3-12 seconds of reference audio for voice cloningApache 2.0 licenseThe model was trained on a single L40S GPU. It’s not SOTA in most cases, can be a bit unstable, and sometimes fails to capture voice likeness.
1 comment
[ 3.0 ms ] story [ 11.7 ms ] thread169M parameters
Streaming support
Zero-shot voice cloning
0.25 RTF on CPU, meaning it generates 30 seconds of audio in 7.5 seconds
Requires 3-12 seconds of reference audio for voice cloning
Apache 2.0 license
The model was trained on a single L40S GPU. It’s not SOTA in most cases, can be a bit unstable, and sometimes fails to capture voice likeness.