BREAKING
Soprano: 80M On-Device TTS Model
0M
parameters
0x
real-time CPU
0GB
under memory
0%
fewer hallucinations
0%
user preference
0+
HF downloads
Runs locally, ships with tools
1pip install soprano-tts
2WebUI, CLI, API
3ONNX & ComfyUI
4CPU, CUDA, MPS
Strengths and current limits
Strengths
Sub-15ms GPU streaming
Runs on a Raspberry Pi
Apache-2.0 license
Limits
English-only, no cloning yet
~1,000 hours of training data
No large benchmark paper
Edge TTS gains momentum
AI NEWS BLITZ
An open-source text-to-speech model called Soprano is drawing developer attention for running fully on-device.