Back: Catalog

MOSS-TTS-Nano

MOSS-TTS-Nano offers real-time CPU extraction and audio copying features as a polylingual speech synthesis model with 100 million parameters. Thanks to the ONNX CPU version, which removes the PyTorch dependency, it can run on a single processor core and be used in web browser extensions. It also provides fine-tuning code and 48 kHz stereo production support for the model.

MO

MOSS-TTS-Nano

New57

OpenMOSS · Voice & Text-to-Speech

STARS4.6K
FORKS568
COMMITS0
CONTRIBUTORS0
VERSION—
UPDATED1 mo ago
PythonSes SenteziCPU ÇıkarımıONNXApache-2.0

Common commercial products in this category: ElevenLabs, Amazon Polly, Google Cloud Text-to-Speech

What can it do?
  • You can perform real-time CPU extraction
  • You can run audio copy workflow
  • You can use the fine-tuning code for the model
Heads up
  • • No published release
User reviews
  • • NeutralGitHub Issue

    Training or fine-tuning script

    “Hi, any training code or fine-tuning code will be very useful our core use is edge first ed tech in Indian languages.if you are planing to release training and fine-tuning will be very useful. Or give a sample code”

Website GitHub

My note

Alternative pages

ElevenLabs alternativesAmazon Polly alternativesGoogle Cloud Text-to-Speech alternatives

More in: Voice & Text-to-Speech