[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M735A4S9AQ24JSST0EW0SJ01":3,"skill-same:01M735A4S9AQ24JSST0EW0SJ01":46},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":27,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M735A4S9AQ24JSST0EW0SJ01","moss-tts-nano",null,"Horonomos-laps\u002FYana-AI","Horonomos-laps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F355299122?v=4","01M76B3QPXE88ET2SQPDPVATZT"," Horonomos-laps","01M72ZQRJPCYPSSWT4D00VJR2A",13,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fmoss-tts-nano\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"# moss-tts-nano\n\n**Source:** OpenMOSS\u002FMOSS-TTS-Nano (Apache 2.0)\n**Model:** 0.1B params · 48kHz stereo · CPU-friendly · multilingual\n\n## When to use\n\n- Add TTS \u002F voice output to any agent or CLI tool\n- Voice clone from a reference audio sample\n- Realtime streaming speech generation without GPU\n- Long-text narration with automatic chunking\n\n## Do NOT use for\n\n- High-fidelity studio audio (use a larger model)\n- Languages outside Chinese \u002F English \u002F supported list\n\n---\n\n## Setup\n\n```bash\n# ONNX version — no PyTorch needed at inference time (recommended)\npip install onnxruntime numpy soundfile\ngit clone https:\u002F\u002Fgithub.com\u002FOpenMOSS\u002FMOSS-TTS-Nano\ncd MOSS-TTS-Nano\n# Download ONNX weights from HuggingFace\nhuggingface-cli download OpenMOSS-Team\u002FMOSS-TTS-Nano-100M-ONNX --local-dir .\u002Fonnx_weights\nhuggingface-cli download OpenMOSS-Team\u002FMOSS-Audio-Tokenizer-Nano-ONNX --local-dir .\u002Fonnx_tokenizer\n\n# PyTorch version — full features + finetuning\nconda create -n moss-tts python=3.10\nconda activate moss-tts\npip install -r requirements.txt\nhuggingface-cli download OpenMOSS-Team\u002FMOSS-TTS-Nano --local-dir .\u002Fcheckpoints\n```\n\n---\n\n## Basic inference\n\n```python\n# ONNX CPU (fastest, no GPU needed)\nfrom onnx_tts_runtime import OnnxTTSRuntime\n\ntts = OnnxTTSRuntime(\n    tts_model_dir=\".\u002Fonnx_weights\",\n    tokenizer_dir=\".\u002Fonnx_tokenizer\",\n)\n\n# Simple generation\ntts.generate(\n    text=\"Hello, this is MOSS TTS Nano.\",\n    output_path=\"output.wav\",\n)\n\n# Voice clone from reference audio\ntts.generate(\n    text=\"Hello, this is MOSS TTS Nano.\",\n    reference_audio=\"path\u002Fto\u002Fspeaker.wav\",\n    output_path=\"cloned_output.wav\",\n)\n```\n\n```bash\n# CLI — generate\nmoss-tts-nano generate \\\n  --text \"Xin chào, đây là MOSS TTS Nano.\" \\\n  --reference-audio speaker.wav \\\n  --output output.wav\n\n# CLI — serve FastAPI\nmoss-tts-nano serve --host 0.0.0.0 --port 8000\n```\n\n---\n\n## Streaming inference\n\n```python\nfrom moss_tts_nano_runtime import MossTTSNanoRuntime\n\nruntime = MossTTSNanoRuntime(checkpoint_dir=\".\u002Fcheckpoints\")\n\n# Stream audio chunks as they're generated\nfor chunk in runtime.stream(\n    text=\"Long text here...\",\n    reference_audio=\"speaker.wav\",\n):\n    play_audio_chunk(chunk)  # feed to speaker \u002F buffer\n```\n\n---\n\n## FastAPI server\n\n```python\n# Start server\npython app_onnx.py  # ONNX version (recommended for prod)\npython app.py       # PyTorch version\n\n# POST \u002Ftts\nimport httpx, base64, soundfile as sf, io\n\nresp = httpx.post(\"http:\u002F\u002Flocalhost:8000\u002Ftts\", json={\n    \"text\": \"Hello from YAMTAM.\",\n    \"reference_audio\": None,   # omit for default voice\n})\naudio_bytes = base64.b64decode(resp.json()[\"audio_base64\"])\nsf.write(\"out.wav\", *sf.read(io.BytesIO(audio_bytes)))\n```\n\n---\n\n## Finetuning\n\n```bash\ncd finetuning\u002F\n\n# Prepare dataset: each line = {\"text\": \"...\", \"audio\": \"path\u002Fto\u002Ffile.wav\"}\npython prepare_data.py --input your_data\u002F --output dataset\u002F\n\n# Finetune (single GPU or CPU)\npython train.py \\\n  --base-checkpoint ..\u002Fcheckpoints \\\n  --dataset dataset\u002F \\\n  --output-dir finetuned\u002F \\\n  --epochs 10 \\\n  --batch-size 4\n\n# Inference with finetuned checkpoint\npython ..\u002Finfer.py --checkpoint finetuned\u002F --text \"...\" --output out.wav\n```\n\n---\n\n## YAMTAM agent integration pattern\n\n```python\nimport httpx\n\ndef yamtam_speak(text: str, voice: str | None = None) -> bytes:\n    \"\"\"Call local MOSS-TTS-Nano server, return WAV bytes.\"\"\"\n    payload = {\"text\": text}\n    if voice:\n        payload[\"reference_audio\"] = voice\n    r = httpx.post(\"http:\u002F\u002Flocalhost:8000\u002Ftts\", json=payload, timeout=30)\n    r.raise_for_status()\n    import base64\n    return base64.b64decode(r.json()[\"audio_base64\"])\n```\n\n---\n\n## Model variants\n\n| Model | Size | Notes |\n|-------|------|-------|\n| MOSS-TTS-Nano | 0.1B | PyTorch, full features |\n| MOSS-TTS-Nano-ONNX | 0.1B | No PyTorch, 2× faster on CPU |\n| MOSS-TTS (full) | larger | Higher quality, more languages |\n\nHuggingFace: `OpenMOSS-Team\u002FMOSS-TTS-Nano`\nModelScope: `openmoss\u002FMOSS-TTS-Nano`\n\n---\n\n## Supported languages\n\nChinese (Mandarin) · English · (expanding via finetuning)\n\n## License\n\nApache 2.0 — free for commercial use.\n\n## References\n\n- Repo: https:\u002F\u002Fgithub.com\u002FOpenMOSS\u002FMOSS-TTS-Nano\n- Paper: https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.18090\n- Demo: https:\u002F\u002Fopenmoss.github.io\u002FMOSS-TTS-Nano-Demo\u002F\n- HF Space: https:\u002F\u002Fhuggingface.co\u002Fspaces\u002FOpenMOSS-Team\u002FMOSS-TTS-Nano\n",{},"main","481dcd7dd2e288b9d627a2bd017db70e64e6c6fa",".claude\u002Fskills\u002Fmoss-tts-nano",2,"https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI","https:\u002F\u002Fyana.vutam.link\u002F","https:\u002F\u002Fgithub.com\u002FHoronomos-laps","https:\u002F\u002Fyana.vutam.link","An open-source governed runtime & execution environment for multi-agent AI systems.","2026-11-14 13:24:09",{"source":7,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Horonomos-laps\u002FYana-AI --skill moss-tts-nano",{"tool":38,"command":39},"bunx","bunx skills add Horonomos-laps\u002FYana-AI --skill moss-tts-nano",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Horonomos-laps\u002FYana-AI --skill moss-tts-nano","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fmoss-tts-nano\u002FSKILL.md",true,[],[47,55,62,70,78,86],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":51,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":18},"01M735GKET5YVYKAY62W2P5YXB","openai--sentry--sentry","Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform read-only queries with the bundled script and require `SENTRY_AUTH_TOKEN`.","MIT","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fopenai--sentry--sentry\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":18},"01M73DCAP83T17HY7SMGK7MGFE","ito-basket-compare","Compare Itô prediction-market baskets against a user's knowledge base, portfolio notes, financial context, watchlist, or research thesis. Use for read-only basket comparison and gap analysis without investment advice or live trading.","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fito-basket-compare\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":66,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M734CYEMZFDR3KH6SW0JP8TD","implementing-network-traffic-baselining","Build network traffic baselines from NetFlow\u002FIPFIX data using Python pandas for statistical analysis, z-score anomaly detection, and hourly\u002Fdaily traffic pattern profiling","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-network-traffic-baselining\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":74,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M73ASZ6NJRJM44Z2P84NGQ3Q","detecting-evasion-techniques-in-endpoint-logs","Detects defense evasion techniques used by adversaries in endpoint logs including log tampering, timestomping, process injection, and security tool disabling. Use when investigating suspicious endpoint behavior, building detection rules for evasion tactics, or conducting threat hunting for stealthy adversary activity. Activates for requests involving evasion detection, defense evasion analysis, log tampering detection, or MITRE ATT&CK TA0005.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002Fcore\u002Fskills\u002Fdetecting-evasion-techniques-in-endpoint-logs\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M734AFNXD06Z78QRK0VKGT7Q","implementing-microsegmentation-with-guardicore","Implementing microsegmentation using Akamai Guardicore Segmentation to map application dependencies, create granular network policies, visualize east-west traffic flows, and enforce least-privilege communication between workloads across data centers and cloud.","https:\u002F\u002Fgithub.com\u002Fyanacuti1121\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fimplementing-microsegmentation-with-guardicore\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M736TK27QMCXK0DVCH25SJN5","ramdisk-tmpfs-patterns","https:\u002F\u002Fgithub.com\u002FHoronomos-laps\u002FYana-AI\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Framdisk-tmpfs-patterns\u002FSKILL.md",[],[]]