Agent skill · creative production · aradotso
moss-tts-nano-speech
Expert skill for using MOSS-TTS-Nano, a 0.1B parameter multilingual real-time TTS model that runs on CPU with voice cloning support.
Why this skill is useful
Adds executable scripts and detailed usage patterns for real-time multilingual TTS generation and voice cloning that aren't widely documented.
What it needs
Requires conda, git, python installed locally. About 5k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
MOSS-TTS-Nano Speech Generation Skill Skill by ara.so — Daily 2026 Skills collection. MOSS-TTS-Nano is an open-source multilingual tiny TTS model (0.1B parameters) from MOSI.AI and the OpenMOSS team. It uses an Audio Tokenizer + LLM autoregressive pipeline to generate 48 kHz stereo speech in real time, supports 20 languages, voice cloning, streaming inference, and runs on CPU without a GPU. Installation Conda (recommended) Fix WeTextProcessing if it fails After pip install -e . the moss-tts-nano CLI command is available in the active environment. Model Weights Models are auto-downloaded from Hugging Face on first run: TTS model: OpenMOSS-Team/MOSS-TTS-Nano Audio tokenizer: OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano ModelScope mirrors are available at openmoss/MOSS-TTS-Nano and openmoss/MOSS-Audio-Tokenizer-Nano. CLI Commands Generate speech (voice clone mode) Output defaults to generatedaudio/mossttsnanooutput.wav. Generate from a text file (long-form) Launch local web demo Opens at http://127.0.0.1:18083 — model stays loaded in memory for fast repeated requests. Direct Python entrypoint Output: generatedaudio/inferoutput.wav Python API Usage Basic voice clone inference English voice clone Streaming inference (low latency) Long-text synthesis with chunked voice cloning FastAPI HTTP endpoint usage When the server is running (moss-tts-nano serve or python app.py): Streaming HTTP response (real-time web playback) Supported Languages Code Language Code Language Code Language ------ ----------- ------ ----------- ------ ---------- zh Chinese en English de German es Spanish fr French ja Japanese it Italian hu Hungarian ko Korean ru Russian fa Persian ar Arabic pl Polish pt Portuguese cs Czech da Danish sv Swedish el Greek tr Turkish The language is inferred automatically from the input text and the reference audio. No explicit language code parameter is required for basic usage. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/moss-tts-nano-speech