# moss-tts-nano-speech

A skill that shows the agent how to run MOSS-TTS-Nano, a tiny multilingual speech model with voice cloning that works on CPU.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 478 installs · ★ 88
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/moss-tts-nano-speech/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/moss-tts-nano-speech

## What it does

MOSS-TTS-Nano comes from MOSI.AI and the OpenMOSS team: 0.1B parameters, an audio tokenizer paired with an autoregressive LLM, stereo output at 48 kHz. Twenty languages are covered, and the token stream runs at 12.5 Hz. The skill hands the agent working recipes — the `moss-tts-nano generate` CLI, `infer.py`, the `MossTTSNanoInference` Python class, and the HTTP routes of the local server.

Voice cloning takes a reference WAV through `--prompt-speech` or `--prompt-audio-path`, and the same timbre carries across the whole text. Long documents are split automatically while the speaker stays the same. Streaming via `infer_stream` returns chunks as they are produced, which cuts the wait before the first sound.

Setup runs through conda with Python 3.12: `conda create -n moss-tts-nano python=3.12 -y`, then clone the repo, `pip install -r requirements.txt` and `pip install -e .`. If `WeTextProcessing` fails to build, the instructions include a workaround with `pynini` and a GitHub fork. Weights download from Hugging Face on the first run, so that run needs a network connection.

The local web demo starts with `moss-tts-nano serve` and answers on `http://127.0.0.1:18083`; the model stays in memory, so later requests skip the load. Language is picked up from the text and the reference audio, no code parameter needed.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill moss-tts-nano-speech -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/moss-tts-nano-speech/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/moss-tts-nano-speech/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill moss-tts-nano-speech -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/moss-tts-nano-speech/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill moss-tts-nano-speech -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/moss-tts-nano-speech/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/trending-skills moss-tts-nano-speech
```

2. **Manually: put the files in place**
- File: `.github/skills/moss-tts-nano-speech/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill moss-tts-nano-speech -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/trending-skills --path skills/moss-tts-nano-speech
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/moss-tts-nano-speech/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/trending-skills --skill moss-tts-nano-speech -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/trending-skills/tree/HEAD/skills/moss-tts-nano-speech/SKILL.md

## When to use it
- clone a voice from a short reference clip
- synthesize speech in 20 languages without a GPU
- stream audio chunks for low-latency playback
- narrate a long document in one consistent voice
- run a local HTTP speech endpoint

## Example prompts
- Generate speech from `my_script.txt` using the voice in `assets/audio/zh_1.wav`
- Show me how to call `MossTTSNanoInference` for streaming synthesis
- Start the MOSS-TTS-Nano web demo and show which endpoint to hit

## Similar
- [skill-creator](https://affpapa.org/en/nevibecode/skills/skill-creator.md) — skill · 414180 installs
- [writing-for-agents](https://affpapa.org/en/nevibecode/skills/writing-for-agents.md) — skill · 466719 installs
- [media-use](https://affpapa.org/en/nevibecode/skills/media-use.md) — skill · 1100000 installs
- [mcp-builder](https://affpapa.org/en/nevibecode/skills/mcp-builder.md) — skill · 130949 installs
- [subagent-driven-development](https://affpapa.org/en/nevibecode/skills/subagent-driven-development.md) — skill · 237746 installs
- [orchestration](https://affpapa.org/en/nevibecode/skills/orchestration.md) — skill · 349800 installs

From the same set: [reason-machines/trending-skills](https://affpapa.org/en/nevibecode/by/reason-machines/trending-skills.md) — 186 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md