BREAKING
TinyTTS: 1.6M-param speech model
0M
parameters
0MB
ONNX FP16
0x
real-time CPU
CPU real-time factor by model
TinyTTS ONNX53
Piper26
Kokoro3
Parameter count vs rivals
TinyTTS1.62
Piper63
Kokoro82
Strengths and current limits
Strengths
Apache 2.0, VITS-based
44.1 kHz audio output
Python and Node.js installs
Limits
English-only
No zero-shot voice cloning
Training code not released
Tiny footprint, big speed
AI NEWS BLITZ
A new open-source text-to-speech model runs entirely on CPU with just 1.6 million parameters.