moss-tts-nano-speech
reason-machines475 installs
Turn your text into speech in a cloned voice.
What it does
Generates multilingual speech locally with MOSS-TTS-Nano, using reference audio to clone a voice.
When to use it
Use for local speech generation, voice cloning, or streaming audio generation.
How to use it
Give it text to synthesize; it generates a WAV file using a reference voice, with bundled sample audio shown.
What you provide
- text to synthesize
Uses
Latest review
What you need · 2
The recommended installation uses conda to create and activate a Python 3.12 environment.
The model needs approximately 1–2 GB of RAM.
Access · 3
This skill
Hugging Face
Read
Downloads model weights from Hugging Face
MOSS-TTS-Nano
Execute
Installs MOSS-TTS-Nano and its dependencies