Back to Details

local-ai-use

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Local AI Use (route image, TTS, STT through Lemonade)

本地AI使用（通过Lemonade路由图像、TTS、STT）

This is a meta-skill. You run it once. After that, every later request that needs image generation, text-to-speech, or speech-to-text uses the local Lemonade Server instead of a cloud API. The agent's own LLM keeps handling text; only the expensive multimodal calls move on-device.
The skill does three things:
  1. Makes sure local Lemonade is installed and running. If no modern 
    lemonade
    CLI is found, the setup script installs the latest version of Lemonade on the user's behalf. Modern Lemonade has no 
    serve
    command — the Lemonade service (the 
    lemond
    daemon) auto-starts on install and is managed by the OS — so the setup script waits for the service and, if it stays down, prints the exact OS-specific command to start it (e.g. 
    sudo systemctl start lemond
    on Linux).
  2. Verifies that local Lemonade is reachable.
  3. Drops a 
    Local AI Use
    block into the workspace 
    AGENTS.md
     so the agent reads the routing rule on every later turn, in Cursor, Claude Code, Codex, Gemini CLI, and any other agent that respects 
    AGENTS.md
    .
Requires modern Lemonade (v10.1.0 or newer). Modern Lemonade unified everything under one 
lemonade
CLI (
lemonade status
, 
lemonade pull
, ...) driving an always-on 
lemond
service. This skill targets that and installs Lemonade only from the official installers (see below) — never via 
pip install lemonade-sdk
, which is a separate, older release line. If an older/incompatible 
lemonade
is already on the PATH (from any channel — an old 
.msi
/
.deb
or a pip install), it will shadow the modern CLI; uninstall it first (see the removal commands in Step 1a) before running this skill.
Models are not downloaded during setup. Each default model is pulled lazily, on first use, by the routing rule (e.g. the first image request pulls the image model). This keeps setup fast and avoids gigabytes of downloads the user may never need.
这是一项元技能。只需运行一次。此后所有需要图像生成、文本转语音（TTS）或语音转文本（STT）的请求，都将使用本地Lemonade Server而非云API。Agent自身的LLM仍处理文本内容；仅昂贵的多模态调用会转移到设备端执行。
该技能实现三项功能：
  1. 确保本地Lemonade已安装并运行。若未找到新版
    lemonade
    CLI，设置脚本将为用户自动安装最新版本的Lemonade。新版Lemonade无
    serve
    命令——Lemonade服务（
    lemond
    守护进程）在安装时自动启动，并由操作系统管理——因此设置脚本会等待服务启动，若服务始终未启动，则打印特定于操作系统的启动命令（例如Linux上的
    sudo systemctl start lemond
    ）。
  2. 验证本地Lemonade是否可访问。
  3. 在工作区的
    AGENTS.md
    中添加
    Local AI Use
    块    ，以便Agent在后续每次交互时读取路由规则，适用于Cursor、Claude Code、Codex、Gemini CLI及任何支持
    AGENTS.md
    的Agent。
要求使用新版Lemonade（v10.1.0或更高版本）。新版Lemonade将所有功能统一到单个
lemonade
CLI下（
lemonade status
、
lemonade pull
等），驱动始终运行的
lemond
服务。本技能针对此版本，且仅从官方安装程序安装Lemonade（见下文）——绝不通过
pip install lemonade-sdk
安装，这是独立的旧版本分支。若PATH中已存在旧版/不兼容的
lemonade
（来自任何渠道——旧版
.msi
/
.deb
或pip安装），它会覆盖新版CLI；请先卸载旧版本（见步骤1a中的卸载命令），再运行此技能。
设置过程中不会下载模型。每个默认模型会在首次使用时通过路由规则懒加载（例如首次图像请求时拉取图像模型）。这样可保持设置速度快，避免下载用户可能永远不需要的数GB数据。

When to use this skill

使用场景

Use this skill when all of the following are true:
  • The user wants local Lemonade. If it is not yet installed, the setup script installs the latest version for them automatically.
  • The user accepts the default Lemonade endpoint 
    http://localhost:13305
    .
  • The user wants the change to be persistent across future turns and agent restarts (the rule is written to disk).
If the user is instead embedding Lemonade as a private subprocess inside an app installer, do not use this skill; use 
local-ai-app-integration
instead.
当所有以下条件满足时，使用此技能：
  • 用户需要本地Lemonade。若尚未安装，设置脚本将自动为用户安装最新版本。
  • 用户接受默认Lemonade端点
    http://localhost:13305
    。
  • 用户希望更改在未来交互和Agent重启后持久生效（规则将写入磁盘）。
若用户是要将Lemonade作为私有子进程嵌入应用安装程序中，请不要使用此技能；改用
local-ai-app-integration
。

Prerequisites

前提条件

  • OS: Windows 11 x64, Ubuntu/Debian x64, or macOS (beta).
  • Lemonade: the setup script installs it if missing. It downloads and silently installs the latest version (Windows 
    lemonade.msi
    , the Ubuntu/Debian 
    ppa:lemonade-team/stable
    PPA, or the macOS 
    .pkg
    ). The 
    lemond
    service auto-starts after install; the script waits for it rather than launching it. On Linux/macOS the install needs 
    sudo
    . Pass 
    --no-install
    if the user wants to install it themselves instead.
  • Disk: ~8 GB free for the three default models (SD-Turbo + Whisper-Tiny
    • kokoro-v1), plus ~0.1 GB for the installer itself.
  • Network: required for the install download and the first 
    lemonade pull
    of each model. After that, every modality runs offline.
  • 操作系统：Windows 11 x64、Ubuntu/Debian x64或macOS（测试版）。
  • Lemonade：若缺失，设置脚本将自动安装。它会下载并静默安装最新版本（Windows的
    lemonade.msi
    、Ubuntu/Debian的
    ppa:lemonade-team/stable
    PPA或macOS的
    .pkg
    ）。
    lemond
    服务在安装后自动启动；脚本会等待服务启动而非手动启动。在Linux/macOS上安装需要
    sudo
    权限。若用户希望自行安装，可传递
    --no-install
    参数。
  • 磁盘空间：约8GB可用空间，用于存储三个默认模型（SD-Turbo + Whisper-Tiny + kokoro-v1），加上约0.1GB的安装程序本身。
  • 网络：安装下载和首次拉取每个模型时需要网络。之后，所有多模态功能均可离线运行。

The opinionated path

标准化流程

Run this checklist top to bottom. Track progress against it; do not move on until each step verifies.
[ ] 1. Ensure Lemonade Server is installed and running (auto-install if missing)
[ ] 2. Install the routing rule into the workspace AGENTS.md
The single command that does both steps in one shot is:
bash
python scripts/setup_local_ai.py
Always run this script first — even if Lemonade is already installed and the server is already running, and even before generating a single image. Writing the routing rule into 
AGENTS.md
is what makes this skill complete; skipping it because "Lemonade is already up" leaves the workspace unconfigured for future turns. The script is safe to run in that case: it detects the running service, skips the install, and just writes the rule.
It auto-installs the latest version of Lemonade if no modern 
lemonade
CLI is found, waits for the auto-started 
lemond
service, then writes the rule. The script is idempotent: re-running it on a fully configured workspace is a no-op apart from a healthcheck. Read the sections below for what to do when each step fails.
按从上到下的顺序执行以下检查清单。跟踪进度；每一步验证通过后再进行下一步。
[ ] 1. 确保Lemonade Server已安装并运行（缺失时自动安装）
[ ] 2. 将路由规则安装到工作区的AGENTS.md中
可一次性完成两步的命令是：
bash
python scripts/setup_local_ai.py
请始终先运行此脚本——即使Lemonade已安装且服务已运行，甚至在生成第一张图像之前。将路由规则写入
AGENTS.md
是完成此技能的关键；不要因为“Lemonade已启动”而跳过此步骤，否则工作区在未来交互中将未配置。在此情况下运行脚本是安全的：它会检测到运行中的服务，跳过安装步骤，仅写入规则。
若未找到新版
lemonade
CLI，它会自动安装最新版本的Lemonade，等待自动启动的
lemond
服务，然后写入规则。该脚本具有幂等性：在已完全配置的工作区重新运行时，除了健康检查外不会产生任何操作。若某一步失败，请阅读以下章节了解解决方法。

Step 1: ensure Lemonade Server is installed and running

步骤1：确保Lemonade Server已安装并运行

scripts/setup_local_ai.py
handles this end to end, but here is what it does so you can do it by hand or debug it:
1a. Is a modern 
lemonade
CLI installed? Run 
lemonade status
. The check is by capability, not by name: modern Lemonade prints 
Server is running...
or 
Server is not running
. If instead you get an "invalid choice" / usage error, the 
lemonade
on 
PATH
is an old, incompatible build that predates the unified CLI (v10.1.0) — do not use it. It could have come from any install channel, so remove it based on how it was installed, then re-run this skill (or install Lemonade manually):
Installed viaUninstall with
Windows 
.msi
winget uninstall -e --id AMD.LemonadeServer
, or Settings > Apps > Installed apps > Lemonade Server > Uninstall
Ubuntu/Debian apt/PPA
sudo apt remove lemonade-server
pip
pip uninstall lemonade-sdk
macOS 
.pkg
Delete the installed 
Lemonade.app
/ remove the package receipt
Never try to drive or auto-remove it for the user.
If no 
lemonade
is found at all, install the latest version on the user's behalf:
OSInstall
WindowsDownload 
lemonade.msi
from the latest release and run 
msiexec /i lemonade.msi /qn
(silent, per-user, no elevation).
Ubuntu/Debian
sudo add-apt-repository -y ppa:lemonade-team/stable && sudo apt-get update && sudo apt-get install -y lemonade-server
(the apt package is 
lemonade-server
; the CLI you then run is 
lemonade
)
macOS (beta)Download the 
Lemonade-<ver>-Darwin.pkg
from the latest release and run 
sudo installer -pkg Lemonade-<ver>-Darwin.pkg -target /
.
After a Windows install the CLI lands in 
%LOCALAPPDATA%\lemonade_server
and is added to the user PATH (new shells only); the setup script probes that directory so it works in the same run.
1b. Is the service running? Check 
lemonade status --json
. The 
lemond
service auto-starts on install — there is no 
lemonade serve
in modern Lemonade.
lemonade status
says		Action
Server is running on port 13305
Continue to Step 2.
Server is not running
Wait a few seconds for the auto-started service (the script polls 
/api/v1/health
). If it stays down, start it via the OS service manager: 
sudo systemctl start lemond
(Linux system install) or 
systemctl --user start lemond
(per-user install); 
launchctl load /Library/LaunchDaemons/com.lemonade.server.plist
(macOS); the Lemonade tray app or 
Start-Service lemond
(Windows).
Only if the automatic install genuinely fails (no 
apt-get
, no 
sudo
, download blocked) should you stop and point the user at https://lemonade-server.ai/docs/guide/install/.
The rest of this skill assumes the endpoint is 
http://localhost:13305/api/v1
and no API key is required (the system-wide server defaults to no auth on loopback). If the user has set 
LEMONADE_API_KEY
, the routing rule template in 
templates/local-ai-rule.md
shows where to add the 
Authorization
header.
scripts/setup_local_ai.py
会端到端处理此步骤，但以下是它的具体操作，以便手动执行或调试：
1a. 是否已安装新版
lemonade
CLI？ 运行
lemonade status
。检查依据是功能而非版本号：新版Lemonade会显示
Server is running...
或
Server is not running
。若返回“invalid choice”/使用错误，则PATH中的
lemonade
是旧版、不兼容的构建（早于统一CLI的v10.1.0）——请勿使用。它可能来自任何安装渠道，请根据安装方式卸载，然后重新运行此技能（或手动安装Lemonade）：
安装方式卸载命令
Windows 
.msi
winget uninstall -e --id AMD.LemonadeServer
，或通过设置>应用>已安装应用>Lemonade Server>卸载
Ubuntu/Debian apt/PPA
sudo apt remove lemonade-server
pip
pip uninstall lemonade-sdk
macOS 
.pkg
删除已安装的
Lemonade.app
/ 移除包收据
请勿尝试为用户自动卸载。
若未找到任何
lemonade
，则为用户安装最新版本：
操作系统安装方式
Windows从最新版本下载
lemonade.msi
，并运行
msiexec /i lemonade.msi /qn
（静默、按用户安装、无需提升权限）。
Ubuntu/Debian
sudo add-apt-repository -y ppa:lemonade-team/stable && sudo apt-get update && sudo apt-get install -y lemonade-server
（apt包名为
lemonade-server
；之后运行的CLI是
lemonade
）
macOS（测试版）从最新版本下载
Lemonade-<ver>-Darwin.pkg
，并运行
sudo installer -pkg Lemonade-<ver>-Darwin.pkg -target /
。
Windows安装后，CLI会位于
%LOCALAPPDATA%\lemonade_server
，并添加到用户PATH中（仅新shell生效）；设置脚本会探测此目录，因此在同一次运行中即可生效。
1b. 服务是否正在运行？ 检查
lemonade status --json
。
lemond
服务在安装时自动启动——新版Lemonade没有
lemonade serve
命令。
lemonade status
输出		操作
Server is running on port 13305
继续步骤2。
Server is not running
等待几秒让自动启动的服务启动（脚本会轮询
/api/v1/health
）。若仍未启动，通过操作系统服务管理器启动：
sudo systemctl start lemond
（Linux系统级安装）或
systemctl --user start lemond
（按用户安装）；
launchctl load /Library/LaunchDaemons/com.lemonade.server.plist
（macOS）；Lemonade托盘应用或
Start-Service lemond
（Windows）。
只有当自动安装确实失败（无
apt-get
、无
sudo
权限、下载被阻止）时，才需停止操作并引导用户访问https://lemonade-server.ai/docs/guide/install/。
本技能的其余部分假设端点为
http://localhost:13305/api/v1
且无需API密钥（系统级服务器默认在回环接口上无认证）。若用户设置了
LEMONADE_API_KEY
，
templates/local-ai-rule.md
中的路由规则模板会显示添加
Authorization
头的位置。

Default modality models (pulled on first use, not during setup)

默认多模态模型（首次使用时拉取，非设置期间）

Setup does not download these. The installed rule pulls each one the first time that modality is requested. They are the Lite Collection defaults from Lemonade OmniRouter, sized to keep token-and-cost savings real on commodity hardware:
ModalityModelSizeWhy this default
Image generation
SD-Turbo
~5 GBSingle-step generation, runs on CPU and AMD iGPU/dGPU
Text-to-speech
kokoro-v1
~0.3 GBOnly TTS model Lemonade currently supports; CPU-only, low latency
Speech-to-text
Whisper-Tiny
~0.1 GBSmallest Whisper; fast on CPU. Upgrade to 
Whisper-Large-v3-Turbo
if accuracy matters more than latency.
To write a different model ID into the rule, pass it to the setup script. For example, to make future image requests use SDXL:
bash
python scripts/setup_local_ai.py --image-model SDXL-Turbo
That model ID is written into the installed 
AGENTS.md
rule and pulled on its first use. The same pattern works for 
--tts-model
and 
--stt-model
. For larger / higher-quality alternatives (
SDXL-Turbo
, 
Flux-2-Klein-4B
, 
Whisper-Large-v3-Turbo
), see the model picker in reference.md.
设置过程中不会下载这些模型。已安装的规则会在首次请求对应模态时拉取相应模型。它们是Lemonade OmniRouter的精简集合默认模型，大小适合在普通硬件上实现真正的令牌和成本节约：
模态模型大小默认原因
图像生成
SD-Turbo
~5 GB单步生成，可在CPU和AMD iGPU/dGPU上运行
文本转语音
kokoro-v1
~0.3 GB当前Lemonade仅支持此TTS模型；仅需CPU，低延迟
语音转文本
Whisper-Tiny
~0.1 GB最小的Whisper模型；在CPU上运行速度快。若更看重准确性而非延迟，可升级为
Whisper-Large-v3-Turbo
。
要在规则中写入不同的模型ID，可将其传递给设置脚本。例如，要让未来的图像请求使用SDXL：
bash
python scripts/setup_local_ai.py --image-model SDXL-Turbo
该模型ID会写入已安装的
AGENTS.md
规则中，并在首次使用时拉取。同样的模式适用于
--tts-model
和
--stt-model
。如需更大/更高质量的替代模型（
SDXL-Turbo
、
Flux-2-Klein-4B
、
Whisper-Large-v3-Turbo
），请参阅reference.md中的模型选择器。

Step 2: install the routing rule into AGENTS.md

步骤2：将路由规则安装到AGENTS.md中

The rule is a Markdown block stored in 
templates/local-ai-rule.md
. Append it to the workspace's 
AGENTS.md
(create the file if missing). Both Cursor and Claude Code load 
AGENTS.md
automatically on every turn, so the agent will see the rule on its next message without any further setup.
scripts/setup_local_ai.py
does this for you. It bakes the selected endpoint and model IDs into the rule, surrounded by stable markers so re-running the script replaces the block in place rather than appending a second copy. The markers look like:
<!-- BEGIN amd-skills:local-ai-use -->
...rule...
<!-- END amd-skills:local-ai-use -->
If you write the file by hand, keep those exact markers. The script relies on them for idempotent updates.
If the user's agent only respects a different convention, mirror the same block to:
  • CLAUDE.md
    (Claude Code, project-scoped) or 
    ~/.claude/CLAUDE.md
    (global)
  • .cursor/rules/local-ai-use.mdc
    (Cursor user/project rules)
  • GEMINI.md
    (Gemini CLI)
The rule's content is identical; only the file location changes.
规则是存储在
templates/local-ai-rule.md
中的Markdown块。将其追加到工作区的
AGENTS.md
中（若文件缺失则创建）。Cursor和Claude Code会在每次交互时自动加载
AGENTS.md
，因此Agent会在下一次消息中看到该规则，无需额外设置。
scripts/setup_local_ai.py
会为你完成此操作。它会将选定的端点和模型ID嵌入规则中，并使用稳定标记包裹，以便重新运行脚本时替换现有块而非追加副本。标记如下：
<!-- BEGIN amd-skills:local-ai-use -->
...rule...
<!-- END amd-skills:local-ai-use -->
若手动编写文件，请保留这些精确标记。脚本依赖它们实现幂等更新。
若用户的Agent仅支持其他约定，请将相同块复制到：
  • CLAUDE.md
    （Claude Code，项目级）或
    ~/.claude/CLAUDE.md
    （全局）
  • .cursor/rules/local-ai-use.mdc
    （Cursor用户/项目规则）
  • GEMINI.md
    （Gemini CLI）
规则内容完全相同；仅文件位置不同。

What changes after this skill runs

技能运行后的变化

From the next turn onward, the agent reads the rule in 
AGENTS.md
on every message. The rule explicitly tells the agent:
  • For image generation: call 
    POST /api/v1/images/generations
    on the local server. Do not call any cloud image API and do not use the built-in 
    GenerateImage
    tool (that path bills tokens to the cloud provider).
  • For text-to-speech: call 
    POST /api/v1/audio/speech
    . Do not call cloud TTS providers (OpenAI TTS, ElevenLabs, etc.).
  • For speech-to-text: call 
    POST /api/v1/audio/transcriptions
    . Do not call cloud transcription providers.
  • Fallback: only fall back to a cloud API after one local attempt has failed and the user has been told the local call failed. Never silently fall back; the whole point of this skill is to keep cost predictable.
The agent's own text reasoning continues to use whatever LLM Cursor / Claude Code / Codex is configured with. This skill does not redirect chat tokens; it only redirects the multimodal calls that would otherwise leave the machine.
从下一次交互开始，Agent会在每次消息时读取
AGENTS.md
中的规则。规则明确告知Agent：
  • 图像生成：调用本地服务器的
    POST /api/v1/images/generations
    接口。请勿调用任何云图像API，也不要使用内置的
    GenerateImage
    工具（该路径会向云提供商支付令牌费用）。
  • 文本转语音：调用
    POST /api/v1/audio/speech
    接口。请勿调用云TTS提供商（OpenAI TTS、ElevenLabs等）。
  • 语音转文本：调用
    POST /api/v1/audio/transcriptions
    接口。请勿调用云转录提供商。
  • 回退机制：仅在本地尝试失败且已告知用户本地调用失败后，才回退到云API。绝不静默回退；本技能的核心目的是保持成本可预测。
Agent自身的文本推理仍使用Cursor/Claude Code/Codex配置的LLM。本技能不会重定向聊天令牌；仅重定向原本会离开设备的多模态调用。

Troubleshooting cheatsheet

故障排除速查表

SymptomCauseRecovery
lemonade: command not found
CLI not installedRe-run 
python scripts/setup_local_ai.py
(auto-installs the latest version). If it just installed on Windows, open a new shell so the user PATH refreshes, or the script will find it under 
%LOCALAPPDATA%\lemonade_server
.
status
gives an "invalid choice" / usage error		An old, incompatible 
lemonade
(pre-v10.1.0, from any install channel) is shadowing the modern CLI		Uninstall it the way it was installed (see the Step 1a table: 
winget uninstall -e --id AMD.LemonadeServer
/ 
sudo apt remove lemonade-server
/ 
pip uninstall lemonade-sdk
), then re-run the setup script or install Lemonade from the docs link.
Server is not running
lemond
service stopped		Start it via the OS service manager — 
sudo systemctl start lemond
/ 
systemctl --user start lemond
(Linux), 
launchctl load /Library/LaunchDaemons/com.lemonade.server.plist
(macOS), or the tray app / 
Start-Service lemond
(Windows). There is no 
lemonade serve
.
POST /v1/images/generations
returns 404 model not found		Image model not downloaded
lemonade pull SD-Turbo
and retry.
lemonade pull
keeps printing 
Progress: NN%
but never finishes		Download target is a bad path (out of space, no write permission, quota, read-only mount). The write error may surface only in the server log while the console keeps showing progressCheck the target and free space first: 
GET /api/v1/system-info
reports 
models_dir
and 
model_storage.free_bytes
. If a pull stalls, read the recent lines of the server log (typically 
lemonade-server.log
in the OS temp dir) for the real error (e.g. a download/write failure like 
CURL code 23
, or an out-of-space message), then point the download at a writable disk with room.
Image generation is slow on CPU (~4–5 min)sd-cpp on CPU backendInstall the GPU backend on supported AMD hardware: 
lemonade backends install sd-cpp:rocm
.
POST /v1/audio/transcriptions
returns 400 unsupported format		Input is not 16 kHz mono WAVRe-encode with 
ffmpeg -i in.* -ar 16000 -ac 1 out.wav
.
POST /v1/audio/speech
returns 404		TTS model not downloaded
lemonade pull kokoro-v1
.
401 Unauthorized on every requestUser has set 
LEMONADE_API_KEY
Add 
Authorization: Bearer $LEMONADE_API_KEY
to every request and to the rule block.
症状原因解决方法
lemonade: command not found
CLI未安装重新运行
python scripts/setup_local_ai.py
（自动安装最新版本）。若刚在Windows上安装，请打开新shell以刷新用户PATH，或脚本会在
%LOCALAPPDATA%\lemonade_server
下找到它。
status
返回“invalid choice”/使用错误		旧版、不兼容的
lemonade
（v10.1.0之前，来自任何安装渠道）覆盖了新版CLI		按安装方式卸载旧版本（见步骤1a的表格：
winget uninstall -e --id AMD.LemonadeServer
/ 
sudo apt remove lemonade-server
/ 
pip uninstall lemonade-sdk
），然后重新运行设置脚本或从文档链接安装Lemonade。
Server is not running
lemond
服务已停止		通过操作系统服务管理器启动——
sudo systemctl start lemond
/ 
systemctl --user start lemond
（Linux），
launchctl load /Library/LaunchDaemons/com.lemonade.server.plist
（macOS），或托盘应用 / 
Start-Service lemond
（Windows）。没有
lemonade serve
命令。
POST /v1/images/generations
返回404模型未找到		图像模型未下载运行
lemonade pull SD-Turbo
后重试。
lemonade pull
持续显示
Progress: NN%
但从未完成		下载目标路径存在问题（空间不足、无写入权限、配额限制、只读挂载）。写入错误可能仅在服务器日志中显示，而控制台仍显示进度首先检查目标路径和可用空间：
GET /api/v1/system-info
会报告
models_dir
和
model_storage.free_bytes
。若拉取停滞，请读取服务器日志的最新行（通常位于操作系统临时目录中的
lemonade-server.log
）以获取真实错误（例如下载/写入失败如
CURL code 23
，或空间不足消息），然后将下载指向有足够空间的可写磁盘。
CPU上图像生成速度慢（约4-5分钟）使用CPU后端的sd-cpp在支持的AMD硬件上安装GPU后端：
lemonade backends install sd-cpp:rocm
。
POST /v1/audio/transcriptions
返回400不支持的格式		输入不是16kHz单声道WAV使用
ffmpeg -i in.* -ar 16000 -ac 1 out.wav
重新编码。
POST /v1/audio/speech
返回404		TTS模型未下载运行
lemonade pull kokoro-v1
。
所有请求均返回401未授权用户设置了
LEMONADE_API_KEY
在每个请求和规则块中添加
Authorization: Bearer $LEMONADE_API_KEY
。

Verification checklist

验证清单

Mark this skill complete only when all of the following are true:
  • lemonade status --json
    reports the server running on port 13305.
  • The workspace 
    AGENTS.md
    contains the 
    amd-skills:local-ai-use
    block. This is required even when Lemonade was already installed and running — generating an image alone does not complete the skill.
  • On a follow-up turn, asking the agent to "generate an image of X" causes it to POST to 
    http://localhost:13305/api/v1/images/generations
    (pulling the model on first use) rather than calling a cloud tool.
If any box is unchecked, the user is still paying cloud cost for at least one modality.
仅当所有以下条件满足时，才标记此技能已完成：
  • lemonade status --json
    报告服务器在端口13305上运行。
  • 工作区的
    AGENTS.md
    包含
    amd-skills:local-ai-use
    块。即使Lemonade已安装并运行，这也是必需的——仅生成图像并不代表技能完成。
  • 在后续交互中，要求Agent“生成一张X的图像”时，它会向
    http://localhost:13305/api/v1/images/generations
    发送POST请求（首次使用时拉取模型），而非调用云工具。
若有任何一项未勾选，用户仍会为至少一种模态支付云服务费用。

Reference

参考资料

For the full model picker, alternate-quality options, the complete endpoint reference, the API-key flow, and the OmniRouter tool definitions you can hand to an agent's tool-calling loop, see reference.md.
如需完整的模型选择器、替代质量选项、完整的端点参考、API密钥流程以及可传递给Agent工具调用循环的OmniRouter工具定义，请参阅reference.md。