Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add coderzc/open-xiaoai-bridge --skill xiaoai-ttsgit clone --depth 1 https://github.com/coderzc/open-xiaoai-bridgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/coderzc/open-xiaoai-bridge/xiaoai-tts)<a href="https://agentmods.dev/skills/coderzc/open-xiaoai-bridge/xiaoai-tts"><img src="https://agentmods.dev/badge/skills/coderzc/open-xiaoai-bridge/xiaoai-tts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/coderzc/open-xiaoai-bridge/xiaoai-tts"><img src="https://agentmods.dev/badge/skills/coderzc/open-xiaoai-bridge/xiaoai-tts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00127 | $0.01416 |
| Opus 5.5 | $0.00051 | $0.00566 |
| Sonnet 5.5 | $0.00025 | $0.00283 |
| Haiku 4.5 | $0.00013 | $0.00142 |
Grade A, and why
xiaoai-tts scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
XiaoAI TTS
通过 XiaoAI HTTP API 控制小爱音箱播放语音，支持火山引擎豆包 TTS 多情感、多音色、语速调整等高级功能。
前置配置
在 env 中添加：
OPENXIAOAI_BASE_URL="http://192.168.x.x:9092" # OpenXiaoAI 服务地址
使用方法
# 语音播报（优先 Doubao TTS，失败自动回退小爱自带 TTS）
xiaoai-tts tts "你好，我是小爱语音助手"
# 指定音色
xiaoai-tts tts "你好" -s zh_female_vv_uranus_bigtts
# 调整语速（0.8-2.0）
xiaoai-tts tts "你好" --speed 1.2
# 指定情感（仅多情感音色支持）
xiaoai-tts tts "你怎么能这样！" -s zh_male_lengkugege_emo_v2_mars_bigtts -m angry
# 2.0 音色 + 上下文指令
xiaoai-tts tts "这是一个很长的句子" -s zh_female_vv_uranus_bigtts -c "你可以说慢一点吗？"
# 强制使用小爱自带 TTS
xiaoai-tts text "你好"
# 唤醒小爱
xiaoai-tts wakeup
xiaoai-tts wakeup --silent # 静默唤醒
# 状态 / 健康检查
xiaoai-tts status
xiaoai-tts health
# 播放音频
xiaoai-tts file /path/to/audio.mp3
xiaoai-tts url "http://example.com/audio.mp3"
# 查看可用音色
xiaoai-tts voices # 所有音色
xiaoai-tts voices -v 2.0 # 仅 2.0 音色
xiaoai-tts voices -v 1.0 # 仅 1.0 音色
常用音色推荐
用户自定义声音复刻（S_ 前缀）
如果用户想使用自定义复刻音色，引导用户前往 火山引擎声音复刻控制台 上传声音训练专属音色，训练完成后在 音色库 的「我的音色」中复制音色 ID（格式为 S_xxxxxxxx），填入 -s 参数即可使用。
xiaoai-tts tts "你好，我是你的专属语音助手" -s S_xxxxxxxx
注意：声音复刻音色 ID 通常以
S_开头，传入时无需通过xiaoai-tts voices列表验证，直接使用即可。
工作流：
- 用户想使用自定义复刻音色时，引导用户前往火山引擎完成声音训练并获取音色 ID
- 用户拿到音色 ID 后，引导用户将音色昵称和 ID 填入下方表格
- 后续用户提到音色昵称时，直接从表格中查找对应 ID 使用
用户已保存的自定义音色
| 音色名称 | speaker_id | 特点 |
|---|---|---|
| （暂无，引导用户添加） | - | - |
2.0 音色（推荐）
| 音色名称 | speaker_id | 特点 |
|---|---|---|
| Vivi 2.0 | zh_female_vv_uranus_bigtts | 通用场景，情感变化 |
| 小何 2.0 | zh_female_xiaohe_uranus_bigtts | 通用场景 |
| 云舟 2.0 | zh_male_m191_uranus_bigtts | 通用场景 |
| 小天 2.0 | zh_male_taocheng_uranus_bigtts | 通用场景 |
1.0 音色（多情感）
| 音色名称 | speaker_id | 特点 |
|---|---|---|
| 冷酷哥哥 | zh_male_lengkugege_emo_v2_mars_bigtts | 支持 emotion 参数 |
| 高冷御姐 | zh_female_gaolengyujie_emo_v2_mars_bigtts | 支持 emotion 参数 |
| 灿灿 | zh_female_cancan_mars_bigtts | 通用场景 |
| 爽快思思 | zh_female_shuangkuaisisi_moon_bigtts | 通用场景 |
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 118 lines · 127 tokens per session scan A 454ff2773612
xiaoai-tts is a skill published in the GitHub repository coderzc/open-xiaoai-bridge (429 stars, last pushed 18d ago), licensed MIT. It adds 127 tokens to every session and 1,416 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
rosclaw-embodied
A set of rules for completing robot tasks in ROSClaw, a system for running and checking robot work. It covers approved robot files, acceptance evidence, and separate rules for simulation and real hardware.
local-media-smart-device-workflows
Class-level workflow for local context and media/device CLIs: places search, weather, smart lights, Sonos, Spotify, audio analysis, text-to-speech, GIF search, image generation/editing, and 1Password secrets needed by those tools. Use when asked to control local devices, query local places/weather, play media…
findmy
Track Apple devices/AirTags via FindMy.app on macOS.
elon-musk-perspective
A decision guide based on Elon Musk’s public statements and actions. It examines problems through basic constraints, cost breakdowns, skeptical questioning, rapid iteration, and choices between building and outsourcing.
sonoscli
Control Sonos speakers (discover/status/play/volume/group).
camsnap
Capture frames or clips from RTSP/ONVIF cameras.