feat: add Windows real RTC voice device simulator

This commit is contained in:
Codex Local
2026-08-27 11:02:32 +08:00
parent 3b827431c8
commit 5ff1961d79
18 changed files with 6036 additions and 0 deletions
+1
View File
@@ -12,6 +12,7 @@ coverage*.out
*.exe *.exe
/opsconfig /opsconfig
/deploy/server/.env /deploy/server/.env
/deploy/local-rtc/runtime/
bin/ bin/
dist/ dist/
tmp/ tmp/
+10
View File
@@ -185,6 +185,15 @@ docker compose --profile simulation run --rm sim-device
docker compose --profile simulation run --rm -e SIM_SCENARIO=offline,conversation,transcript,telemetry,commands sim-device docker compose --profile simulation run --rm -e SIM_SCENARIO=offline,conversation,transcript,telemetry,commands sim-device
``` ```
在Windows本机使用真实麦克风、扬声器和火山RTC/豆包端到端语音进行联调:
```powershell
.\deploy\local-rtc\configure.ps1
.\deploy\local-rtc\start.ps1
```
然后运行`device-simulator-windows/release/voice-device-simulator-0.1.0-windows-x64.exe`。密钥配置、纯端到端首轮联调范围和操作步骤见[Windows本地真实RTC联调说明](deploy/local-rtc/README.md)。
还可用`SIM_SCENARIO=media`和`SIM_CONVERSATION_ID`验证已授权通话的录音直传、后台校验、延迟删除及设备删除回执;详见`docs/device-integration.md`。 还可用`SIM_SCENARIO=media`和`SIM_CONVERSATION_ID`验证已授权通话的录音直传、后台校验、延迟删除及设备删除回执;详见`docs/device-integration.md`。
执行设备状态、错误和命令结果的批量遥测、幂等、事件判重及冲突回滚烟测: 执行设备状态、错误和命令结果的批量遥测、幂等、事件判重及冲突回滚烟测:
@@ -326,6 +335,7 @@ internal/ 平台公共能力及后续领域模块
migrations/ 仅追加的数据库迁移 migrations/ 仅追加的数据库迁移
openapi/ 对外接口契约基线 openapi/ 对外接口契约基线
web/ 家庭用户和运营网页 web/ 家庭用户和运营网页
device-simulator-windows/ Windows真实音频终端模拟器
deploy/ 容器构建与运行配置 deploy/ 容器构建与运行配置
docs/ 架构决策与研发基线 docs/ 架构决策与研发基线
scripts/ 本地启动和质量检查脚本 scripts/ 本地启动和质量检查脚本
+41
View File
@@ -0,0 +1,41 @@
# Windows 本地真实 RTC 联调
该覆盖层只用于本机联调,不访问阿里云服务器。它把 API 的 RTC Token 签发器和 Worker 的语音供应商切换到火山引擎,同时保留数据库、Redis、MinIO、Keycloak和告警模拟器在本地 Docker 中运行。
## 1. 生成本地凭据
在项目根目录运行:
```powershell
.\deploy\local-rtc\configure.ps1
```
脚本会以隐藏输入方式依次读取:
- RTC AppKey;
- 火山引擎 AccessKey ID / Secret AccessKey;
- 豆包端到端语音 APP ID / Access Token;
- 豆包音色 ID。
密钥文件只生成到`deploy/local-rtc/runtime`,该目录不会提交到 Git。当前首轮联调使用豆包 S2S-O 纯端到端模式(`OutputMode=0`),平台本地路由仍沿用`s2s_hybrid`模板槽位;这是为了只依赖豆包端到端语音凭据,先验证真实双向音频。后续接入火山方舟 Endpoint 后再切换真正的混合编排模式。
## 2. 启动本地后端
```powershell
.\deploy\local-rtc\start.ps1
```
首次构建需要下载 Docker 基础镜像。脚本会等待`http://localhost:58080/health/ready`可用。
## 3. 启动模拟器
双击`device-simulator-windows/release/voice-device-simulator-0.1.0-windows-x64.exe`,然后:
1. 保持默认本地平台地址、设备 ID 和本地测试设备密钥;
2. 点击“检测平台和音频设备”;
3. 选择麦克风和扬声器;
4. 点击“开始语音聊天”;
5. 看到“豆包语音任务已激活”后直接说话;
6. 点击“结束通话”验证`StopVoiceChat`和RTC离房。
RTC AppKey、火山 AK/SK 和豆包 Access Token 均不进入模拟器安装包,也不会通过渲染页面读取。
+24
View File
@@ -0,0 +1,24 @@
services:
api:
environment:
RTC_APP_ID: ${RTC_APP_ID}
RTC_TOKEN_ISSUER: volcengine
RTC_APP_KEY: ""
RTC_APP_KEY_FILE: /run/secrets/local-rtc/rtc-app-key
volumes:
- ./deploy/local-rtc/runtime/rtc-app-key:/run/secrets/local-rtc/rtc-app-key:ro
worker:
environment:
VOICE_PROVIDER: volcengine
VOLC_ACCESS_KEY_ID: ""
VOLC_ACCESS_KEY_ID_FILE: /run/secrets/local-rtc/volc-access-key-id
VOLC_SECRET_ACCESS_KEY: ""
VOLC_SECRET_ACCESS_KEY_FILE: /run/secrets/local-rtc/volc-secret-access-key
VOLC_RTC_REGION: cn-north-1
VOLC_RTC_API_VERSION: 2024-12-01
VOLC_VOICE_CHAT_TEMPLATE_FILE: /run/secrets/local-rtc/voice-chat-template.json
volumes:
- ./deploy/local-rtc/runtime/volc-access-key-id:/run/secrets/local-rtc/volc-access-key-id:ro
- ./deploy/local-rtc/runtime/volc-secret-access-key:/run/secrets/local-rtc/volc-secret-access-key:ro
- ./deploy/local-rtc/runtime/voice-chat-template.json:/run/secrets/local-rtc/voice-chat-template.json:ro
+118
View File
@@ -0,0 +1,118 @@
[CmdletBinding()]
param(
[string]$RtcAppId = "6a8f92ca43726c017d34cce1",
[switch]$Force
)
$ErrorActionPreference = "Stop"
$scriptDirectory = Split-Path -Parent $MyInvocation.MyCommand.Path
$runtimeDirectory = Join-Path $scriptDirectory "runtime"
$utf8NoBom = [System.Text.UTF8Encoding]::new($false)
function Read-RequiredText {
param([string]$Prompt, [string]$Default = "")
$suffix = if ($Default) { " [$Default]" } else { "" }
$value = Read-Host "$Prompt$suffix"
if ([string]::IsNullOrWhiteSpace($value)) { $value = $Default }
if ([string]::IsNullOrWhiteSpace($value)) { throw "$Prompt 不能为空" }
return $value.Trim()
}
function Read-RequiredSecret {
param([string]$Prompt, [int]$MinimumLength = 1)
$secureValue = Read-Host $Prompt -AsSecureString
$pointer = [Runtime.InteropServices.Marshal]::SecureStringToBSTR($secureValue)
try {
$value = [Runtime.InteropServices.Marshal]::PtrToStringBSTR($pointer)
}
finally {
[Runtime.InteropServices.Marshal]::ZeroFreeBSTR($pointer)
}
if ($value.Length -lt $MinimumLength) { throw "$Prompt 长度不足" }
return $value
}
function Write-SecretFile {
param([string]$Name, [string]$Value)
$target = Join-Path $runtimeDirectory $Name
[IO.File]::WriteAllText($target, $Value, $utf8NoBom)
}
if ($RtcAppId.Length -ne 24) {
throw "RTC AppId 必须正好为 24 个字符"
}
if ((Test-Path -LiteralPath $runtimeDirectory) -and -not $Force) {
throw "本地凭据目录已经存在。确认需要重新配置后使用 -Force。"
}
New-Item -ItemType Directory -Path $runtimeDirectory -Force | Out-Null
Write-Host "`n配置只保存在本机 deploy/local-rtc/runtime,已被 Git 忽略。" -ForegroundColor Cyan
Write-Host "输入密钥时屏幕不会显示字符。`n" -ForegroundColor DarkGray
$rtcAppKey = Read-RequiredSecret "RTC AppKey" 16
$volcAccessKeyId = Read-RequiredText "火山引擎 AccessKey ID"
$volcSecretAccessKey = Read-RequiredSecret "火山引擎 Secret AccessKey"
$doubaoAppId = Read-RequiredText "豆包端到端语音 APP ID"
$doubaoAccessToken = Read-RequiredSecret "豆包端到端语音 Access Token"
$speaker = Read-RequiredText "豆包音色 ID" "zh_female_vv_jupiter_bigtts"
$template = [ordered]@{
schema_version = "voice-chat-template-bundle-v1"
templates = [ordered]@{
s2s_hybrid = [ordered]@{
AgentConfig = [ordered]@{
TargetUserId = @()
UserId = ""
WelcomeMessage = "您好,我是豆包语音助手。今天想聊些什么?"
EnableConversationStateCallback = $false
}
Config = [ordered]@{
InterruptMode = 0
S2SConfig = [ordered]@{
Provider = "volcano"
OutputMode = 0
ProviderParams = [ordered]@{
app = [ordered]@{
appid = $doubaoAppId
token = $doubaoAccessToken
}
dialog = [ordered]@{
extra = [ordered]@{
model = "O"
strict_audit = $true
audit_response = "抱歉,这个话题我暂时无法回答。我们换个轻松的话题吧。"
}
}
asr = [ordered]@{
extra = [ordered]@{
end_smooth_window_ms = 1200
}
}
tts = [ordered]@{
speaker = $speaker
}
}
}
}
}
}
}
Write-SecretFile "rtc-app-key" $rtcAppKey
Write-SecretFile "volc-access-key-id" $volcAccessKeyId
Write-SecretFile "volc-secret-access-key" $volcSecretAccessKey
[IO.File]::WriteAllText(
(Join-Path $runtimeDirectory "voice-chat-template.json"),
($template | ConvertTo-Json -Depth 20),
$utf8NoBom
)
[IO.File]::WriteAllText(
(Join-Path $runtimeDirectory "local-rtc.env"),
"RTC_APP_ID=$RtcAppId`n",
$utf8NoBom
)
Write-Host "`n本地真实 RTC 配置已生成。" -ForegroundColor Green
Write-Host "下一步运行: .\deploy\local-rtc\start.ps1" -ForegroundColor Green
+57
View File
@@ -0,0 +1,57 @@
[CmdletBinding()]
param([switch]$NoBuild)
$ErrorActionPreference = "Stop"
$scriptDirectory = Split-Path -Parent $MyInvocation.MyCommand.Path
$projectRoot = Resolve-Path (Join-Path $scriptDirectory "..\..")
$runtimeDirectory = Join-Path $scriptDirectory "runtime"
$environmentFile = Join-Path $runtimeDirectory "local-rtc.env"
$requiredFiles = @(
"rtc-app-key",
"volc-access-key-id",
"volc-secret-access-key",
"voice-chat-template.json",
"local-rtc.env"
)
foreach ($name in $requiredFiles) {
if (-not (Test-Path -LiteralPath (Join-Path $runtimeDirectory $name) -PathType Leaf)) {
throw "缺少 $name,请先运行 .\deploy\local-rtc\configure.ps1"
}
}
Push-Location $projectRoot
try {
$arguments = @(
"compose",
"-f", "compose.yaml",
"-f", "deploy/local-rtc/compose.override.yaml",
"--env-file", $environmentFile,
"up", "-d"
)
if (-not $NoBuild) { $arguments += "--build" }
$arguments += @(
"postgres", "redis", "minio", "keycloak", "migrate", "seed",
"callbacks", "mock-alert-receiver", "mock-provider", "api", "worker"
)
& docker @arguments
if ($LASTEXITCODE -ne 0) { throw "Docker Compose 启动失败" }
Write-Host "`n等待本地 API 就绪..." -ForegroundColor Cyan
$deadline = [DateTime]::UtcNow.AddMinutes(3)
do {
Start-Sleep -Seconds 2
try {
$health = Invoke-RestMethod -Uri "http://localhost:58080/health/ready" -TimeoutSec 3
if ($health) { break }
}
catch { }
} while ([DateTime]::UtcNow -lt $deadline)
if (-not $health) { throw "本地 API 未在三分钟内就绪,请检查 docker compose logs api worker" }
Write-Host "本地真实 RTC 后端已就绪:http://localhost:58080" -ForegroundColor Green
Write-Host "现在可以启动 Windows 语音终端模拟器。" -ForegroundColor Green
}
finally {
Pop-Location
}
+4
View File
@@ -0,0 +1,4 @@
node_modules/
dist/
release/
*.log
+23
View File
@@ -0,0 +1,23 @@
# Windows 语音终端模拟器
该程序使用Electron和火山引擎Web RTC SDK模拟一台真实语音终端。它采集Windows麦克风、加入平台分配的RTC房间、发布本地音频、订阅并播放豆包智能体音频,并通过设备v2接口完成激活、状态等待、心跳、Token续签和结束通话。
## 构建
```powershell
Set-Location .\device-simulator-windows
npm install
npm run build
```
输出:`release/voice-device-simulator-0.1.0-windows-x64.exe`。
## 安全边界
- RTC AppKey、火山AK/SK和豆包Access Token只存在本地后端的受保护文件中;
- 模拟器安装包只接收平台签发的短期RTC Token;
- 设备签名密钥只驻留Electron主进程内存,不写入浏览器存储;
- 当前构建只允许设备API地址指向`localhost`或`127.0.0.1`,避免误连服务器环境;
- 关闭软件或结束通话时停止音频采集并销毁RTC引擎。
完整本地启动顺序见[本地真实RTC联调说明](../deploy/local-rtc/README.md)。
+208
View File
@@ -0,0 +1,208 @@
const { app, BrowserWindow, ipcMain, session } = require("electron");
const crypto = require("node:crypto");
const fs = require("node:fs");
const path = require("node:path");
app.commandLine.appendSwitch("autoplay-policy", "no-user-gesture-required");
let deviceConfig = null;
let desiredConfigRevision = 1;
function createWindow() {
const window = new BrowserWindow({
width: 1220,
height: 820,
minWidth: 980,
minHeight: 700,
backgroundColor: "#eef3f0",
autoHideMenuBar: true,
title: "语音终端模拟器",
webPreferences: {
preload: path.join(__dirname, "preload.cjs"),
contextIsolation: true,
nodeIntegration: false,
sandbox: true,
},
});
const devArgument = process.argv.find((argument) => argument.startsWith("--dev-server-url="));
const devServerURL = devArgument ? devArgument.slice("--dev-server-url=".length) : "";
if (devServerURL) {
window.loadURL(devServerURL);
} else {
window.loadFile(path.join(__dirname, "..", "dist", "index.html"));
}
const screenshotPath = process.env.SIMULATOR_SCREENSHOT_PATH;
if (screenshotPath) {
window.webContents.once("did-finish-load", () => {
setTimeout(async () => {
const image = await window.webContents.capturePage();
fs.writeFileSync(screenshotPath, image.toPNG());
app.quit();
}, 1200);
});
}
}
function ensureLoopbackURL(value) {
const parsed = new URL(String(value || ""));
const loopback = parsed.hostname === "127.0.0.1" || parsed.hostname === "localhost" || parsed.hostname === "[::1]";
if (!loopback || (parsed.protocol !== "http:" && parsed.protocol !== "https:")) {
throw new Error("本地测试只允许连接 localhost 或 127.0.0.1");
}
return parsed.origin;
}
function configure(input) {
const apiURL = ensureLoopbackURL(input?.apiURL);
const deviceID = String(input?.deviceID || "").trim();
const deviceSecret = String(input?.deviceSecret || "");
if (!/^[0-9a-f-]{36}$/i.test(deviceID)) {
throw new Error("设备 ID 必须是 UUID");
}
if (deviceSecret.length < 32) {
throw new Error("设备密钥至少需要 32 个字符");
}
deviceConfig = { apiURL, deviceID, deviceSecret };
return { apiURL, deviceID };
}
function nonce() {
return crypto.randomBytes(16).toString("hex");
}
function signedHeaders(method, requestURI, body) {
if (!deviceConfig) throw new Error("请先连接本地平台");
const timestamp = new Date().toISOString();
const requestNonce = nonce();
const digest = crypto.createHash("sha256").update(body).digest("hex");
const canonical = [method.toUpperCase(), requestURI, timestamp, requestNonce, digest].join("\n");
const signature = crypto.createHmac("sha256", deviceConfig.deviceSecret).update(canonical).digest("base64url");
return {
"X-Device-Id": deviceConfig.deviceID,
"X-Device-Timestamp": timestamp,
"X-Device-Nonce": requestNonce,
"X-Device-Content-SHA256": digest,
"X-Device-Signature": signature,
};
}
async function deviceRequest(method, requestPath, payload, idempotencyKey) {
if (!deviceConfig) throw new Error("请先连接本地平台");
const target = new URL(requestPath, `${deviceConfig.apiURL}/`);
const body = payload === undefined ? "" : JSON.stringify(payload);
const headers = signedHeaders(method, `${target.pathname}${target.search}`, body);
headers.Accept = "application/json";
if (body) headers["Content-Type"] = "application/json";
if (idempotencyKey) headers["Idempotency-Key"] = idempotencyKey;
const response = await fetch(target, { method, headers, body: body || undefined });
const text = await response.text();
let parsed;
try {
parsed = text ? JSON.parse(text) : {};
} catch {
parsed = { message: text };
}
if (!response.ok) {
const code = parsed?.error?.code || parsed?.code || `HTTP_${response.status}`;
const message = parsed?.error?.message || parsed?.message || "本地平台请求失败";
throw new Error(`${code}: ${message}`);
}
return parsed?.data ?? parsed;
}
ipcMain.handle("sim:configure", (_event, input) => configure(input));
ipcMain.handle("sim:probe", async () => {
const query = new URLSearchParams({
firmware_version: "0.3.0-windows-rtc",
board_rev: "windows-x64",
rtc_sdk_version: "web-4.69.0-electron",
codec: "opus",
sample_rate: "48000",
network: "windows-local",
device_time: new Date().toISOString(),
});
const bootstrap = await deviceRequest("GET", `/device/v2/bootstrap?${query.toString()}`);
const configuration = await deviceRequest("GET", "/device/v2/config");
desiredConfigRevision = Number(configuration.revision || bootstrap?.device?.config_revision || 1);
return { bootstrap, configuration, desiredConfigRevision };
});
ipcMain.handle("sim:create-conversation", async () => deviceRequest("POST", "/device/v2/conversations", {
device_time: new Date().toISOString(),
monotonic_ms: Math.max(0, Math.round(performance.now())),
capabilities: {
rtc: true,
audio_tracks: ["near", "far"],
upload_resume: true,
rtc_credential_renewal: true,
},
network: { type: "windows-local" },
requested_goal: "open_conversation",
}, `windows-create-${nonce()}`));
ipcMain.handle("sim:activate-conversation", async (_event, input) => deviceRequest(
"POST",
`/device/v2/conversations/${encodeURIComponent(input.conversationID)}/activate`,
{
joined_at: new Date().toISOString(),
room_id: input.roomID,
rtc_user_id: input.userID,
rtc_join_result: "success",
config_revision: desiredConfigRevision,
connection_reference: "windows-electron-web-rtc",
},
`windows-activate-${nonce()}`,
));
ipcMain.handle("sim:get-conversation", async (_event, conversationID) => deviceRequest(
"GET",
`/device/v2/conversations/${encodeURIComponent(conversationID)}`,
));
ipcMain.handle("sim:heartbeat", async (_event, input) => deviceRequest(
"POST",
`/device/v2/conversations/${encodeURIComponent(input.conversationID)}/heartbeat`,
{
sequence_no: input.sequenceNo,
device_time: new Date().toISOString(),
monotonic_ms: Math.max(0, Math.round(performance.now())),
conversation_status: "ACTIVE",
rtc: { joined: true, uplink: true, downlink: true },
network: { type: "windows-local" },
firmware_version: "0.3.0-windows-rtc",
reported_config_revision: desiredConfigRevision,
rtc_credential_expires_at: input.credentialExpiresAt,
recording_queue: { pending_segments: 0, failed_segments: 0 },
command_results: [],
},
));
ipcMain.handle("sim:stop-conversation", async (_event, input) => deviceRequest(
"POST",
`/device/v2/conversations/${encodeURIComponent(input.conversationID)}/stop`,
{
reason: input.reason || "windows_user_hangup",
device_time: new Date().toISOString(),
last_heartbeat_sequence: input.lastHeartbeatSequence || 0,
rtc_left: true,
recording: { near_segments: 0, far_segments: 0 },
},
`windows-stop-${nonce()}`,
));
app.whenReady().then(() => {
session.defaultSession.setPermissionCheckHandler((_webContents, permission) => permission === "media");
session.defaultSession.setPermissionRequestHandler((_webContents, permission, callback) => callback(permission === "media"));
createWindow();
});
app.on("window-all-closed", () => {
if (process.platform !== "darwin") app.quit();
});
app.on("activate", () => {
if (BrowserWindow.getAllWindows().length === 0) createWindow();
});
@@ -0,0 +1,11 @@
const { contextBridge, ipcRenderer } = require("electron");
contextBridge.exposeInMainWorld("deviceSimulator", {
configure: (input) => ipcRenderer.invoke("sim:configure", input),
probe: () => ipcRenderer.invoke("sim:probe"),
createConversation: () => ipcRenderer.invoke("sim:create-conversation"),
activateConversation: (input) => ipcRenderer.invoke("sim:activate-conversation", input),
getConversation: (conversationID) => ipcRenderer.invoke("sim:get-conversation", conversationID),
heartbeat: (input) => ipcRenderer.invoke("sim:heartbeat", input),
stopConversation: (input) => ipcRenderer.invoke("sim:stop-conversation", input),
});
+13
View File
@@ -0,0 +1,13 @@
<!doctype html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<meta http-equiv="Content-Security-Policy" content="default-src 'self'; script-src 'self'; style-src 'self'; connect-src 'self' https: wss: http://127.0.0.1:* http://localhost:*; media-src 'self' blob:; worker-src 'self' blob:; img-src 'self' data:;" />
<title>语音终端模拟器</title>
</head>
<body>
<main id="app"></main>
<script type="module" src="/src/main.ts"></script>
</body>
</html>
File diff suppressed because it is too large Load Diff
+46
View File
@@ -0,0 +1,46 @@
{
"name": "data-terminal-voice-device-simulator",
"version": "0.1.0",
"private": true,
"description": "Windows real-audio device simulator for the data terminal cloud platform",
"main": "electron/main.cjs",
"scripts": {
"dev": "concurrently -k \"vite --host 127.0.0.1 --port 5177\" \"wait-on http://127.0.0.1:5177 && electron . --dev-server-url=http://127.0.0.1:5177\"",
"typecheck": "tsc --noEmit",
"build:renderer": "vite build",
"start": "npm run build:renderer && electron .",
"build": "npm run typecheck && npm run build:renderer && electron-builder --win portable"
},
"dependencies": {
"@volcengine/rtc": "4.69.0"
},
"devDependencies": {
"concurrently": "^9.2.1",
"electron": "44.0.0",
"electron-builder": "26.15.3",
"typescript": "^5.9.2",
"vite": "^7.1.3",
"wait-on": "^8.0.4"
},
"build": {
"appId": "cn.dataterminal.voice-device-simulator",
"productName": "语音终端模拟器",
"artifactName": "voice-device-simulator-${version}-windows-${arch}.${ext}",
"directories": {
"output": "release"
},
"files": [
"dist/**/*",
"electron/**/*",
"package.json"
],
"win": {
"target": [
{
"target": "portable",
"arch": ["x64"]
}
]
}
}
}
+40
View File
@@ -0,0 +1,40 @@
type SimulatorConfiguration = {
apiURL: string;
deviceID: string;
deviceSecret: string;
};
type RTCGrant = {
app_id: string;
room_id: string;
user_id: string;
agent_user_id: string;
token: string;
expires_at: string;
};
type CreatedConversation = {
conversation_id: string;
status: string;
rtc: RTCGrant;
session: {
engine_mode: string;
heartbeat_interval_sec: number;
allocation_expires_at: string;
};
};
interface Window {
deviceSimulator: {
configure(input: SimulatorConfiguration): Promise<{ apiURL: string; deviceID: string }>;
probe(): Promise<Record<string, unknown>>;
createConversation(): Promise<CreatedConversation>;
activateConversation(input: { conversationID: string; roomID: string; userID: string }): Promise<Record<string, unknown>>;
getConversation(conversationID: string): Promise<{ status: string; action: string; failure_code?: string }>;
heartbeat(input: { conversationID: string; sequenceNo: number; credentialExpiresAt: string }): Promise<{
actions?: Array<{ type: string; rtc?: RTCGrant }>;
desired_config_revision?: number;
}>;
stopConversation(input: { conversationID: string; reason: string; lastHeartbeatSequence: number }): Promise<Record<string, unknown>>;
};
}
+413
View File
@@ -0,0 +1,413 @@
import VERTC, {
IRTCEngine,
LocalAudioPropertiesInfo,
MediaType,
RemoteAudioPropertiesInfo,
RoomProfileType,
} from "@volcengine/rtc";
import "./style.css";
const EngineEventsTypes = VERTC.events;
type Phase = "idle" | "checking" | "ready" | "joining" | "waiting" | "active" | "stopping" | "error";
const state: {
phase: Phase;
engine?: IRTCEngine;
conversation?: CreatedConversation;
credentialExpiresAt?: string;
heartbeatSequence: number;
heartbeatTimer?: number;
statusTimer?: number;
startedAt?: number;
durationTimer?: number;
agentJoined: boolean;
agentSpeaking: boolean;
microphoneVolume: number;
agentVolume: number;
} = {
phase: "idle",
heartbeatSequence: 0,
agentJoined: false,
agentSpeaking: false,
microphoneVolume: 0,
agentVolume: 0,
};
const app = document.querySelector<HTMLElement>("#app")!;
app.innerHTML = `
<section class="shell">
<header class="hero">
<div>
<p class="eyebrow">WINDOWS · REAL RTC DEVICE</p>
<h1>语音终端模拟器</h1>
<p class="subtitle">使用真实麦克风和扬声器,验证“终端入房—豆包进房—双向语音—打断—结束”的完整链路。</p>
</div>
<div class="overall" id="overallStatus"><span class="pulse"></span><strong>尚未连接</strong></div>
</header>
<section class="status-grid" aria-label="链路状态">
<article class="status-card"><span>本地平台</span><strong id="apiStatus">未检测</strong><small id="apiDetail">localhost</small></article>
<article class="status-card"><span>RTC 房间</span><strong id="rtcStatus">未加入</strong><small id="rtcDetail">等待开始</small></article>
<article class="status-card"><span>豆包智能体</span><strong id="agentStatus">未进房</strong><small id="agentDetail">等待 StartVoiceChat</small></article>
<article class="status-card"><span>通话时长</span><strong id="duration">00:00</strong><small id="modeDetail">处理方式:—</small></article>
</section>
<section class="content-grid">
<article class="panel setup-panel">
<div class="panel-heading"><div><p class="eyebrow">LOCAL SETUP</p><h2>本地设备配置</h2></div><span class="safe">密钥仅驻留内存</span></div>
<label>本地平台地址<input id="apiURL" value="http://localhost:58080" autocomplete="off" /></label>
<label>模拟设备 ID<input id="deviceID" value="10000000-0000-0000-0000-000000000511" autocomplete="off" /></label>
<label>设备签名密钥<input id="deviceSecret" type="password" value="local-simulated-device-secret-32-bytes-minimum" autocomplete="off" /></label>
<div class="row">
<label>麦克风<select id="microphone"><option value="">默认麦克风</option></select></label>
<label>扬声器<select id="speaker"><option value="">默认扬声器</option></select></label>
</div>
<button class="secondary" id="checkButton">检测平台和音频设备</button>
<p class="hint">RTC AppKey、火山 AK/SK 和豆包 Token 应配置在本地后端,本软件不会读取或保存它们。</p>
</article>
<article class="panel call-panel">
<div class="panel-heading"><div><p class="eyebrow">LIVE CONVERSATION</p><h2>真实双向语音</h2></div><span class="phase-badge" id="phaseBadge">待机</span></div>
<div class="conversation-orb" id="conversationOrb"><div class="orb-core"><span id="orbLabel">准备开始</span></div></div>
<div class="meters">
<div><div class="meter-label"><span>我的麦克风</span><strong id="micValue">0</strong></div><div class="meter"><i id="micMeter"></i></div></div>
<div><div class="meter-label"><span>豆包语音</span><strong id="agentValue">0</strong></div><div class="meter agent"><i id="agentMeter"></i></div></div>
</div>
<div class="call-actions">
<button class="primary" id="startButton" disabled>开始语音聊天</button>
<button class="danger" id="stopButton" disabled>结束通话</button>
</div>
<dl class="session-info">
<div><dt>通话编号</dt><dd id="conversationID">—</dd></div>
<div><dt>RTC 房间</dt><dd id="roomID">—</dd></div>
<div><dt>终端用户</dt><dd id="userID">—</dd></div>
<div><dt>智能体用户</dt><dd id="agentUserID">—</dd></div>
</dl>
</article>
</section>
<section class="panel log-panel">
<div class="panel-heading"><div><p class="eyebrow">EVENT STREAM</p><h2>实时事件</h2></div><button class="text-button" id="clearLog">清空</button></div>
<ol id="eventLog" aria-live="polite"><li><time>系统</time><span>模拟器已启动,等待检测本地环境。</span></li></ol>
</section>
</section>
`;
const $ = <T extends HTMLElement>(id: string) => document.getElementById(id) as T;
const controls = {
apiURL: $<HTMLInputElement>("apiURL"),
deviceID: $<HTMLInputElement>("deviceID"),
deviceSecret: $<HTMLInputElement>("deviceSecret"),
microphone: $<HTMLSelectElement>("microphone"),
speaker: $<HTMLSelectElement>("speaker"),
check: $<HTMLButtonElement>("checkButton"),
start: $<HTMLButtonElement>("startButton"),
stop: $<HTMLButtonElement>("stopButton"),
};
function setText(id: string, value: string) {
$(id).textContent = value;
}
function log(message: string, level: "info" | "success" | "error" = "info") {
const item = document.createElement("li");
item.className = level;
const time = document.createElement("time");
time.textContent = new Date().toLocaleTimeString("zh-CN", { hour12: false });
const content = document.createElement("span");
content.textContent = message;
item.append(time, content);
$("eventLog").prepend(item);
}
function errorMessage(error: unknown): string {
return error instanceof Error ? error.message : String(error);
}
function setPhase(phase: Phase, detail?: string) {
state.phase = phase;
const labels: Record<Phase, string> = {
idle: "待机", checking: "检测中", ready: "已就绪", joining: "正在入房", waiting: "等待豆包", active: "通话中", stopping: "结束中", error: "异常",
};
setText("phaseBadge", labels[phase]);
setText("overallStatus", detail || labels[phase]);
$("overallStatus").className = `overall phase-${phase}`;
$("conversationOrb").className = `conversation-orb phase-${phase}${state.agentSpeaking ? " speaking" : ""}`;
setText("orbLabel", detail || labels[phase]);
controls.start.disabled = phase !== "ready";
controls.stop.disabled = !["joining", "waiting", "active", "error"].includes(phase) || !state.conversation;
controls.check.disabled = ["joining", "waiting", "active", "stopping"].includes(phase);
}
async function configureAndProbe() {
setPhase("checking", "正在检测");
try {
await window.deviceSimulator.configure({
apiURL: controls.apiURL.value,
deviceID: controls.deviceID.value,
deviceSecret: controls.deviceSecret.value,
});
const supported = await VERTC.isSupported();
if (!supported) throw new Error("当前 Electron 环境不支持火山 Web RTC SDK");
const permission = await VERTC.enableDevices({ audio: true, video: false });
if (!permission.audio) throw permission.audioExceptionError || new Error("未获得麦克风权限");
await refreshAudioDevices();
await window.deviceSimulator.probe();
setText("apiStatus", "连接正常");
setText("apiDetail", controls.apiURL.value);
setPhase("ready", "可以开始通话");
log(`环境检测通过,RTC Web SDK ${VERTC.getSdkVersion()}。`, "success");
} catch (error) {
setText("apiStatus", "检测失败");
setText("apiDetail", errorMessage(error));
setPhase("error", "检测失败");
controls.start.disabled = true;
log(`环境检测失败:${errorMessage(error)}`, "error");
}
}
async function refreshAudioDevices() {
const [microphones, speakers] = await Promise.all([
VERTC.enumerateAudioCaptureDevices(),
VERTC.enumerateAudioPlaybackDevices(),
]);
fillDeviceOptions(controls.microphone, microphones, "默认麦克风");
fillDeviceOptions(controls.speaker, speakers, "默认扬声器");
}
function fillDeviceOptions(select: HTMLSelectElement, devices: MediaDeviceInfo[], fallback: string) {
const previous = select.value;
select.replaceChildren(new Option(fallback, ""));
devices.forEach((device, index) => select.add(new Option(device.label || `${fallback} ${index + 1}`, device.deviceId)));
if ([...select.options].some((option) => option.value === previous)) select.value = previous;
}
function registerRTCEvents(engine: IRTCEngine) {
engine.on(EngineEventsTypes.onUserJoined, (event) => {
const userID = event.userInfo.userId;
log(`远端用户已进房:${userID}`, "success");
if (userID === state.conversation?.rtc.agent_user_id) {
state.agentJoined = true;
setText("agentStatus", "已进房");
setText("agentDetail", userID);
}
});
engine.on(EngineEventsTypes.onUserLeave, (event) => {
const userID = event.userInfo.userId;
log(`远端用户已离房:${userID}`);
if (userID === state.conversation?.rtc.agent_user_id) {
state.agentJoined = false;
setText("agentStatus", "已离房");
}
});
engine.on(EngineEventsTypes.onUserPublishStream, async (event) => {
if ((event.mediaType & MediaType.AUDIO) === 0) return;
log(`检测到远端音频流:${event.userId}`, "success");
try {
await engine.subscribeStream(event.userId, MediaType.AUDIO);
await engine.play(event.userId, MediaType.AUDIO);
if (event.userId === state.conversation?.rtc.agent_user_id) {
setText("agentStatus", "语音已连接");
setText("agentDetail", "正在接收豆包音频");
}
} catch (error) {
log(`播放远端音频失败:${errorMessage(error)}`, "error");
}
});
engine.on(EngineEventsTypes.onLocalAudioPropertiesReport, (reports: LocalAudioPropertiesInfo[]) => {
const volume = Math.max(0, ...reports.map((item) => item.audioPropertiesInfo.linearVolume || 0));
updateVolume("mic", volume);
});
engine.on(EngineEventsTypes.onRemoteAudioPropertiesReport, (reports: RemoteAudioPropertiesInfo[]) => {
const agentID = state.conversation?.rtc.agent_user_id;
const volume = Math.max(0, ...reports.filter((item) => !agentID || item.streamKey.userId === agentID).map((item) => item.audioPropertiesInfo.linearVolume || 0));
state.agentSpeaking = volume > 5;
updateVolume("agent", volume);
setPhase(state.phase, state.phase === "active" ? (state.agentSpeaking ? "豆包正在说话" : "请开始说话") : undefined);
});
engine.on(EngineEventsTypes.onConnectionStateChanged, (event) => {
log(`RTC 连接状态:${String(event.state)}`);
});
engine.on(EngineEventsTypes.onError, (event) => {
log(`RTC 错误:${event.errorCode}`, "error");
});
engine.on(EngineEventsTypes.onTokenWillExpire, () => {
log("RTC Token 即将过期,等待心跳续签。", "info");
});
}
function updateVolume(kind: "mic" | "agent", raw: number) {
const value = Math.max(0, Math.min(100, Math.round(raw)));
if (kind === "mic") state.microphoneVolume = value;
else state.agentVolume = value;
$(`${kind}Meter`).style.width = `${value}%`;
setText(`${kind}Value`, String(value));
}
async function startConversation() {
setPhase("joining", "正在申请房间");
controls.start.disabled = true;
try {
const created = await window.deviceSimulator.createConversation();
state.conversation = created;
state.credentialExpiresAt = created.rtc.expires_at;
state.heartbeatSequence = 0;
state.agentJoined = false;
renderSession(created);
log(`平台已分配 RTC 房间 ${created.rtc.room_id}。`, "success");
const engine = VERTC.createEngine(created.rtc.app_id);
state.engine = engine;
registerRTCEvents(engine);
engine.enableAudioPropertiesReport({ interval: 300 });
await engine.startAudioCapture(controls.microphone.value || undefined);
if (controls.speaker.value) await engine.setAudioPlaybackDevice(controls.speaker.value);
await engine.joinRoom(created.rtc.token, created.rtc.room_id, { userId: created.rtc.user_id }, {
isAutoPublish: true,
isAutoSubscribeAudio: true,
isAutoSubscribeVideo: false,
roomProfileType: RoomProfileType.chat,
});
setText("rtcStatus", "已加入");
setText("rtcDetail", created.rtc.room_id);
log("终端已加入 RTC 房间并发布麦克风。", "success");
await window.deviceSimulator.activateConversation({
conversationID: created.conversation_id,
roomID: created.rtc.room_id,
userID: created.rtc.user_id,
});
setPhase("waiting", "正在拉入豆包");
log("平台已提交 StartVoiceChat,等待豆包智能体激活。", "success");
await waitUntilActive(created.conversation_id);
state.startedAt = Date.now();
setPhase("active", "请开始说话");
startTimers(created.session.heartbeat_interval_sec || 15);
log("豆包语音任务已激活,可以开始双向聊天。", "success");
} catch (error) {
setPhase("error", "启动失败");
log(`启动通话失败:${errorMessage(error)}`, "error");
await releaseRTC();
}
}
function renderSession(created: CreatedConversation) {
setText("conversationID", created.conversation_id);
setText("roomID", created.rtc.room_id);
setText("userID", created.rtc.user_id);
setText("agentUserID", created.rtc.agent_user_id);
setText("modeDetail", `处理方式:${created.session.engine_mode}`);
setText("agentStatus", "等待进房");
setText("agentDetail", created.rtc.agent_user_id);
}
async function waitUntilActive(conversationID: string) {
const deadline = Date.now() + 30_000;
while (Date.now() < deadline) {
const result = await window.deviceSimulator.getConversation(conversationID);
if (result.action === "continue" && result.status === "ACTIVE") return;
if (result.action === "leave_room") throw new Error(result.failure_code || `智能体启动失败:${result.status}`);
await new Promise((resolve) => window.setTimeout(resolve, 600));
}
throw new Error("等待豆包进房超时(30秒)");
}
function startTimers(intervalSeconds: number) {
stopTimers();
state.durationTimer = window.setInterval(() => {
if (!state.startedAt) return;
const seconds = Math.floor((Date.now() - state.startedAt) / 1000);
setText("duration", `${String(Math.floor(seconds / 60)).padStart(2, "0")}:${String(seconds % 60).padStart(2, "0")}`);
}, 1000);
state.heartbeatTimer = window.setInterval(() => void sendHeartbeat(), Math.max(5, intervalSeconds) * 1000);
void sendHeartbeat();
}
async function sendHeartbeat() {
if (!state.conversation || !state.credentialExpiresAt || state.phase !== "active") return;
try {
state.heartbeatSequence += 1;
const result = await window.deviceSimulator.heartbeat({
conversationID: state.conversation.conversation_id,
sequenceNo: state.heartbeatSequence,
credentialExpiresAt: state.credentialExpiresAt,
});
for (const action of result.actions || []) {
if (action.type === "renew_rtc_credential" && action.rtc?.token) {
await state.engine?.updateToken(action.rtc.token);
state.credentialExpiresAt = action.rtc.expires_at;
log("RTC Token 已通过设备心跳完成续签。", "success");
}
}
} catch (error) {
log(`设备心跳失败:${errorMessage(error)}`, "error");
}
}
async function stopConversation(reason = "windows_user_hangup") {
if (!state.conversation) return;
setPhase("stopping", "正在结束通话");
stopTimers();
const conversation = state.conversation;
try {
await releaseRTC();
await window.deviceSimulator.stopConversation({
conversationID: conversation.conversation_id,
reason,
lastHeartbeatSequence: state.heartbeatSequence,
});
log("RTC 已离房,平台已提交 StopVoiceChat。", "success");
resetSession();
setPhase("ready", "可以再次通话");
} catch (error) {
log(`结束通话失败:${errorMessage(error)}`, "error");
resetSession();
setPhase("ready", "已释放本地音频");
}
}
async function releaseRTC() {
const engine = state.engine;
state.engine = undefined;
if (!engine) return;
try { await engine.unpublishStream(MediaType.AUDIO); } catch { /* no-op */ }
try { await engine.leaveRoom(); } catch { /* no-op */ }
try { await engine.stopAudioCapture(); } catch { /* no-op */ }
try { VERTC.destroyEngine(engine); } catch { /* no-op */ }
}
function stopTimers() {
if (state.heartbeatTimer) window.clearInterval(state.heartbeatTimer);
if (state.statusTimer) window.clearInterval(state.statusTimer);
if (state.durationTimer) window.clearInterval(state.durationTimer);
state.heartbeatTimer = undefined;
state.statusTimer = undefined;
state.durationTimer = undefined;
}
function resetSession() {
state.conversation = undefined;
state.credentialExpiresAt = undefined;
state.startedAt = undefined;
state.agentJoined = false;
state.agentSpeaking = false;
setText("rtcStatus", "未加入");
setText("rtcDetail", "等待开始");
setText("agentStatus", "未进房");
setText("agentDetail", "等待 StartVoiceChat");
setText("duration", "00:00");
updateVolume("mic", 0);
updateVolume("agent", 0);
}
controls.check.addEventListener("click", () => void configureAndProbe());
controls.start.addEventListener("click", () => void startConversation());
controls.stop.addEventListener("click", () => void stopConversation());
$("clearLog").addEventListener("click", () => $("eventLog").replaceChildren());
window.addEventListener("beforeunload", () => {
stopTimers();
void releaseRTC();
});
setPhase("idle", "尚未连接");
+74
View File
@@ -0,0 +1,74 @@
:root {
font-family: "Microsoft YaHei UI", "Segoe UI", sans-serif;
color: #112d3f;
background: #eef3f0;
font-synthesis: none;
}
* { box-sizing: border-box; }
body { margin: 0; min-width: 980px; min-height: 100vh; background: radial-gradient(circle at 88% 0%, #f5dfbd 0, transparent 30%), linear-gradient(145deg, #edf5f3 0%, #f7f4eb 100%); }
button, input, select { font: inherit; }
button { cursor: pointer; }
button:disabled { cursor: not-allowed; opacity: .45; }
.shell { width: min(1160px, calc(100vw - 48px)); margin: 0 auto; padding: 36px 0 48px; }
.hero { display: flex; align-items: flex-start; justify-content: space-between; gap: 32px; margin-bottom: 26px; }
.eyebrow { color: #c8652a; font-size: 12px; font-weight: 800; letter-spacing: .16em; margin: 0 0 9px; }
h1 { margin: 0; font-family: Georgia, "Microsoft YaHei UI", serif; font-size: 44px; letter-spacing: -.035em; }
h2 { margin: 0; font-size: 23px; }
.subtitle { max-width: 760px; color: #66808e; line-height: 1.8; margin: 12px 0 0; }
.overall { display: flex; align-items: center; min-width: 150px; justify-content: center; padding: 13px 18px; border-radius: 999px; background: rgba(255,255,255,.82); box-shadow: 0 12px 30px rgba(36,64,69,.1); color: #647a82; }
.overall.phase-ready, .overall.phase-active { color: #1a7d57; }
.overall.phase-error { color: #b63d2e; }
.status-grid { display: grid; grid-template-columns: repeat(4, 1fr); gap: 14px; margin-bottom: 16px; }
.status-card, .panel { background: rgba(255,255,255,.9); border: 1px solid rgba(23,61,69,.08); box-shadow: 0 14px 40px rgba(34,61,63,.08); }
.status-card { min-height: 118px; padding: 22px; border-radius: 20px; }
.status-card span { display: block; color: #778b93; font-size: 14px; }
.status-card strong { display: block; margin: 14px 0 6px; font-size: 21px; }
.status-card small { display: block; color: #8da0a6; white-space: nowrap; overflow: hidden; text-overflow: ellipsis; }
.content-grid { display: grid; grid-template-columns: .95fr 1.35fr; gap: 16px; }
.panel { border-radius: 24px; padding: 28px; }
.panel-heading { display: flex; justify-content: space-between; gap: 18px; align-items: flex-start; margin-bottom: 24px; }
.safe, .phase-badge { color: #287858; background: #e8f5ed; border-radius: 999px; padding: 8px 12px; font-size: 12px; font-weight: 700; }
label { display: block; color: #617985; font-size: 13px; margin-bottom: 16px; }
input, select { width: 100%; border: 1px solid #d7e2de; border-radius: 12px; padding: 12px 13px; margin-top: 7px; color: #153244; background: #f9fbfa; outline: none; }
input:focus, select:focus { border-color: #d6783f; box-shadow: 0 0 0 3px rgba(214,120,63,.12); }
.row { display: grid; grid-template-columns: 1fr 1fr; gap: 12px; }
.secondary, .primary, .danger { border: 0; border-radius: 13px; padding: 13px 18px; font-weight: 800; }
.secondary { width: 100%; color: #173b4d; background: #e9f0ee; }
.primary { flex: 1; color: white; background: #d36f32; box-shadow: 0 10px 24px rgba(211,111,50,.22); }
.danger { color: #9d382c; background: #f7e6e2; }
.hint { margin: 14px 0 0; color: #8a9aa0; font-size: 12px; line-height: 1.65; }
.conversation-orb { width: 180px; height: 180px; margin: 6px auto 24px; border-radius: 50%; display: grid; place-items: center; background: radial-gradient(circle, rgba(216,117,56,.17) 0 34%, rgba(31,88,91,.08) 35% 54%, transparent 55%); transition: .3s ease; }
.orb-core { width: 108px; height: 108px; border-radius: 50%; display: grid; place-items: center; text-align: center; padding: 12px; color: white; background: linear-gradient(145deg, #173b4d, #0d2536); box-shadow: 0 18px 34px rgba(14,43,57,.25); }
.conversation-orb.phase-active { animation: breathe 2.8s ease-in-out infinite; }
.conversation-orb.speaking { background: radial-gradient(circle, rgba(76,173,126,.25) 0 34%, rgba(31,116,91,.13) 35% 62%, transparent 63%); }
@keyframes breathe { 50% { transform: scale(1.045); } }
.meters { display: grid; grid-template-columns: 1fr 1fr; gap: 20px; }
.meter-label { display: flex; justify-content: space-between; color: #6c828b; font-size: 12px; margin-bottom: 7px; }
.meter { height: 8px; border-radius: 999px; background: #e4ebe8; overflow: hidden; }
.meter i { display: block; width: 0; height: 100%; background: linear-gradient(90deg, #d36f32, #f0ad58); transition: width .18s linear; }
.meter.agent i { background: linear-gradient(90deg, #2f8d67, #6fc591); }
.call-actions { display: flex; gap: 10px; margin: 24px 0; }
.session-info { display: grid; grid-template-columns: 1fr 1fr; gap: 10px 22px; padding-top: 18px; border-top: 1px solid #edf1ef; }
.session-info div { min-width: 0; }
.session-info dt { color: #8b9ba1; font-size: 11px; }
.session-info dd { margin: 4px 0 0; font-family: Consolas, monospace; font-size: 12px; white-space: nowrap; overflow: hidden; text-overflow: ellipsis; }
.log-panel { margin-top: 16px; padding-bottom: 18px; }
.log-panel .panel-heading { margin-bottom: 12px; }
.text-button { border: 0; color: #748991; background: transparent; }
#eventLog { list-style: none; margin: 0; padding: 0; max-height: 180px; overflow: auto; }
#eventLog li { display: grid; grid-template-columns: 82px 1fr; gap: 12px; padding: 9px 4px; border-bottom: 1px solid #edf1ef; color: #526c78; font-size: 13px; }
#eventLog time { color: #9aa8ad; font-family: Consolas, monospace; }
#eventLog li.success span { color: #247252; }
#eventLog li.error span { color: #ae3b2f; }
@media (max-width: 1050px) {
.status-grid { grid-template-columns: repeat(2, 1fr); }
.content-grid { grid-template-columns: 1fr; }
}
+13
View File
@@ -0,0 +1,13 @@
{
"compilerOptions": {
"target": "ES2022",
"useDefineForClassFields": true,
"module": "ESNext",
"moduleResolution": "Bundler",
"strict": true,
"noEmit": true,
"lib": ["ES2022", "DOM", "DOM.Iterable"],
"skipLibCheck": true
},
"include": ["src/**/*.ts", "vite.config.ts"]
}
+10
View File
@@ -0,0 +1,10 @@
import { defineConfig } from "vite";
export default defineConfig({
base: "./",
build: {
outDir: "dist",
emptyOutDir: true,
sourcemap: true,
},
});