@xopcai/xopc 0.0.354 → 0.0.356

package/dist/src/tui/tui.js

@@ -1,17 +1,17 @@
 import { version } from "../../package.js";
 import { resolveStateDir, resolveXopcDatabasePath } from "../config/paths-state.js";
-import { init_agent_session_key, normalizeAgentId } from "../routing/agent-session-key.js";
-import { resolveEffectiveAgentProfile } from "../config/agent-profile.js";
 import { init_paths } from "../config/paths.js";
+import { init_agent_session_key, normalizeAgentId } from "../routing/agent-session-key.js";
 import { getAllModels, getAllProviders, getApiKey, init_providers, isProviderConfiguredSync } from "../providers/index.js";
+import { ensureStarterAgentsInitialized } from "../agent/starter-agents.js";
+import { loadConfig } from "../config/loader.js";
+import { resolveEffectiveAgentProfile } from "../config/agent-profile.js";
+import "../config/index.js";
+import { MAX_WEBCHAT_ATTACHMENT_FILE_BYTES } from "../gateway/chat-limits.js";
+import { renderWorkflowFinalSummary, renderWorkflowPanel } from "../agent/workflow/snapshot.js";
 import { isTerminalWorkflowRunStatus } from "../workflows/domain/run.js";
 import "../workflows/domain/index.js";
 import { ProjectTrustStore, hasTrustRequiringProjectResources } from "../project-trust/trust-store.js";
-import { MAX_WEBCHAT_ATTACHMENT_FILE_BYTES } from "../gateway/chat-limits.js";
-import { loadConfig } from "../config/loader.js";
-import { renderWorkflowFinalSummary, renderWorkflowPanel } from "../agent/workflow/snapshot.js";
-import { ensureStarterAgentsInitialized } from "../agent/starter-agents.js";
-import "../config/index.js";
 import { runViewToSnapshot } from "../workflows/service/run-view-to-snapshot.js";
 import { resolveTuiConversationId, resolveTuiStartupConversationId } from "../routing/resolve-tui-session-key.js";
 import { applyThemeById, getBashExcludeBorderColor, getBashModeBorderColor, getCustomThemesDir, getThemeExports, getThinkingBorderColor, initTuiTheme, listAvailableThemeIds, resolveThemePalette } from "./theme-manager.js";

package/dist/src/tunnel/frpc-binary.js

@@ -6,8 +6,8 @@ import { FRPC_RELEASES, FRPC_VERSION } from "./frpc-release.js";
 import { join } from "node:path";
 import { chmodSync, createReadStream, createWriteStream, existsSync, mkdirSync, mkdtempSync, renameSync, rmSync } from "node:fs";
 import { createHash } from "node:crypto";
-import { pipeline } from "node:stream/promises";
 import { Readable, Transform } from "node:stream";
+import { pipeline } from "node:stream/promises";
 //#region src/tunnel/frpc-binary.ts
 init_paths();
 init_logger();

package/dist/src/tunnel/gateway-lifecycle.js

@@ -1,9 +1,9 @@
 import { createLogger } from "../utils/logger/index.js";
 import { init_logger } from "../utils/logger.js";
 import { resolveGatewayEffectiveHost } from "../config/gateway-bind.js";
+import { resolveGatewayAuth } from "../gateway/auth.js";
 import { resolveOptionalTunnelRegistrationSecret, resolveTunnelBrokerUrl } from "./env.js";
 import { getTunnelService } from "./tunnel-service.js";
-import { resolveGatewayAuth } from "../gateway/auth.js";
 import { requireTunnelGatewayToken } from "./auth-policy.js";
 import { hasValidTunnelConsent } from "./consent.js";
 import { resolveFrpSubdomainHost } from "./frp-subdomain-host.js";

package/dist/src/voice/language-profile.js

@@ -47,7 +47,7 @@ function initializeVoiceDefaults(config, language = inferProductLanguageFromEnvi
 		providers: {
 			...audio?.providers ?? {},
 			alibaba: {
-				model: "qwen-audio-3.0-asr-flash",
+				model: "qwen-audio-3.1-asr-flash",
 				...audio?.providers?.alibaba ?? {}
 			},
 			openai: {

package/dist/src/voice/metadata/builtin.js

@@ -1,4 +1,5 @@
 import { OPENAI_TTS_MODELS, OPENAI_TTS_VOICES } from "../tts/providers/openai-speech.js";
+import { alibabaTtsVoices as alibabaTtsVoices$1 } from "../tts/providers/alibaba-voices.js";
 import { MINIMAX_TTS_MODELS, MINIMAX_TTS_VOICES } from "../tts/providers/minimax-speech.js";
 import "../tts/providers/index.js";
 import { registerVoiceProviderMetadata } from "./registry.js";
@@ -13,13 +14,16 @@ function options(values, names) {
 	}));
 }
 const alibabaSttModels = [{
+	id: "qwen-audio-3.1-asr-flash",
+	name: "Qwen Audio 3.1 ASR Flash"
+}, {
 	id: "qwen-audio-3.0-asr-flash",
 	name: "Qwen Audio 3.0 ASR Flash"
 }];
 const alibabaTtsModels = [
 	{
 		id: "qwen-tts",
-		name: "Qwen TTS (Recommended)"
+		name: "Qwen TTS (Legacy)"
 	},
 	{
 		id: "qwen-tts-realtime",
@@ -27,47 +31,20 @@ const alibabaTtsModels = [
 	},
 	{
 		id: "qwen3-tts-flash",
-		name: "Qwen3 TTS Flash"
+		name: "Qwen3 TTS Flash (Recommended)"
 	},
 	{
 		id: "qwen3-tts-instruct-flash",
 		name: "Qwen3 TTS Instruct Flash"
 	}
 ];
-const alibabaTtsVoices = [
-	{
-		id: "Cherry",
-		name: "Cherry"
-	},
-	{
-		id: "Ethan",
-		name: "Ethan"
-	},
-	{
-		id: "Serena",
-		name: "Serena"
-	},
-	{
-		id: "Chelsie",
-		name: "Chelsie"
-	},
-	{
-		id: "longxiaochun",
-		name: "Long Xiao Chun (龙小春)"
-	},
-	{
-		id: "longxiaobai",
-		name: "Long Xiao Bai (龙小白)"
-	},
-	{
-		id: "longwan",
-		name: "Long Wan (龙婉)"
-	},
-	{
-		id: "longcheng",
-		name: "Long Cheng (龙呈)"
-	}
-];
+const alibabaTtsVoices = alibabaTtsVoices$1.map(({ id, name, description, gender, category }) => ({
+	id,
+	name: name ?? id,
+	description,
+	gender,
+	style: category
+}));
 const edgeVoices = [
 	{
 		id: "en-US-MichelleNeural",
@@ -161,7 +138,7 @@ const builtinVoiceProviderMetadata = [
 				label: "Model",
 				type: "select",
 				options: alibabaSttModels,
-				defaultValue: "qwen-audio-3.0-asr-flash"
+				defaultValue: "qwen-audio-3.1-asr-flash"
 			},
 			{
 				key: "language",
@@ -356,14 +333,14 @@ const builtinVoiceProviderMetadata = [
 				label: "Model",
 				type: "select",
 				options: alibabaTtsModels,
-				defaultValue: "qwen-tts"
+				defaultValue: "qwen3-tts-flash"
 			},
 			{
 				key: "voice",
 				label: "Voice",
 				type: "select",
 				options: alibabaTtsVoices,
-				defaultValue: "longxiaochun"
+				defaultValue: "Cherry"
 			}
 		],
 		diagnostics: {

package/dist/src/voice/metadata/types.d.ts

@@ -4,6 +4,8 @@ export interface VoiceOptionMetadata {
     id: string;
     name: string;
     description?: string;
+    gender?: string;
+    style?: string;
 }
 export interface VoiceConfigFieldMetadata {
     key: string;

package/dist/src/voice/platform-catalog.d.ts

@@ -24,6 +24,9 @@ export declare function requirePlatformVoiceModel(id: string, mode: VoiceModeCap
             id: string;
             name: string;
             languages: string[];
+            gender?: "female" | "male";
+            style?: string;
+            description?: string;
         }[];
         limits: {
             maxFrameBytes: number;

package/dist/src/voice/realtime/memory-context.js

@@ -6,12 +6,12 @@ import { getSessionConfig, init_config_repository } from "../../storage/sqlite/c
 import { getConversationRouting } from "../../storage/sqlite/conversation-repository.js";
 import { getConversation } from "../../routing/agent-session-key.js";
 import { init_session_key } from "../../routing/session-key.js";
-import { getKnowledgeItem } from "../../knowledge-memory/repository.js";
-import "../../knowledge-memory/index.js";
 import { getUserAssertion } from "../../user-model/repository.js";
 import "../../user-model/index.js";
-import { stripRuntimeContextFromUserMessage } from "../../session/user-message-display.js";
+import { getKnowledgeItem } from "../../knowledge-memory/repository.js";
+import "../../knowledge-memory/index.js";
 import { buildExecutionContext } from "../../agent/context/execution-context.js";
+import { stripRuntimeContextFromUserMessage } from "../../session/user-message-display.js";
 //#region src/voice/realtime/memory-context.ts
 init_session_key();
 init_config_repository();

package/dist/src/voice/realtime/persona-context.js

@@ -1,6 +1,6 @@
 import { init_agent_scope, resolveAgentProfileDir } from "../../agent/agent-scope.js";
-import { resolveEffectiveAgentProfileForSession } from "../../config/agent-profile.js";
 import { DEFAULT_SOUL_FILENAME } from "../../agent/context/workspace.js";
+import { resolveEffectiveAgentProfileForSession } from "../../config/agent-profile.js";
 import { loadProfileBootstrapFiles } from "../../agent/bootstrap/load-bootstrap-files.js";
 import { join } from "node:path";
 import { statSync } from "node:fs";

package/dist/src/voice/realtime/runtime.js

@@ -4,13 +4,14 @@ import { init_changes, onUserContextChange } from "../../user-context/changes.js
 import { decodeVoiceUplinkAudioFrame, encodeVoiceAudioFrame } from "../../../packages/realtime-protocol/src/voice-audio.js";
 import { VOICE_REALTIME_HEARTBEAT_INTERVAL_MS, VOICE_REALTIME_MAX_BINARY_FRAME_BYTES, VOICE_REALTIME_START_TIMEOUT_MS, VOICE_REALTIME_WS_PATH, init_voice, parseVoiceClientJsonFrame, parseVoiceClientMessage } from "../../../packages/realtime-protocol/src/voice.js";
 import { getModelCatalogStore, init_model_catalog_store } from "../../providers/model-catalog-store.js";
-import { getMediaUnderstandingProvider } from "../../media-understanding/registry.js";
-import { resolveSTTProviderChain } from "../stt/factory.js";
-import { mergeSttConfigFromAppConfig } from "../stt/config.js";
 import { ALIBABA_REALTIME_TTS_MODEL } from "../tts/providers/alibaba-speech.js";
 import { resolveSpeechProviderChain } from "../tts/factory.js";
 import { mergeTtsConfigFromAppConfig } from "../tts/merge-config.js";
+import { getMediaUnderstandingProvider } from "../../media-understanding/registry.js";
+import { resolveSTTProviderChain } from "../stt/factory.js";
+import { mergeSttConfigFromAppConfig } from "../stt/config.js";
 import { voiceConversationInstructions } from "./conversation-context.js";
+import { getPersonalAgentByConversation } from "../../personal-agent/repository.js";
 import { createPreauthConnectionBudget } from "../../gateway/security/preauth-connection-budget.js";
 import { createAgentVoiceEngine } from "./agentEngine.js";
 import { resolveOmniRoute } from "./omniRoute.js";
@@ -186,7 +187,21 @@ var VoiceRealtimeRuntime = class {
 		if (!omni && !stt) throw new VoiceSessionCreationError("PROVIDER_UNAVAILABLE", "No configured streaming speech-to-text provider is available", 503);
 		const inputMode = "server_vad";
 		if (stt && !stt.plugin.streamingAudio.turnDetection.includes(inputMode)) throw new VoiceSessionCreationError("PROVIDER_UNAVAILABLE", `Streaming speech-to-text provider does not support ${inputMode}`, 503);
-		const tts = request.mode === "assistant" ? resolveStreamingTts(config) : void 0;
+		const baseTts = request.mode === "assistant" ? resolveStreamingTts(config) : void 0;
+		const personalVoice = request.conversationId ? getPersonalAgentByConversation(request.conversationId)?.voicePreference : null;
+		const tts = baseTts && personalVoice && baseTts.route.provider === personalVoice.provider && baseTts.route.model === personalVoice.model ? {
+			...baseTts,
+			config: {
+				...baseTts.config,
+				providers: {
+					...baseTts.config.providers,
+					[baseTts.route.provider]: {
+						...baseTts.config.providers?.[baseTts.route.provider],
+						voice: personalVoice.voice
+					}
+				}
+			}
+		} : baseTts;
 		if (request.purpose === "conversation") {
 			if (!request.conversationId || !await this.options.sessionExists(request.conversationId)) throw new VoiceSessionCreationError("SESSION_NOT_FOUND", "Conversation session was not found", 404);
 			if (request.mode === "natural" && this.options.sessionBusy(request.conversationId)) throw new VoiceSessionCreationError("SESSION_CONFLICT", "Conversation session already has an active response", 409);

package/dist/src/voice/stt/index.js

@@ -2,10 +2,10 @@ import { openAiTranscriptionProvider } from "./providers/openai-transcription.js
 import { alibabaTranscriptionProvider } from "./providers/alibaba-transcription.js";
 import "./providers/index.js";
 import { resolveSTTProviderChain, resolveSTTProviderConfig, resolveSTTProviderOrder } from "./factory.js";
-import { STTTranscriptionError, transcribe } from "./transcribe-core.js";
 import { isSTTAvailable } from "./availability.js";
-import { mergeSttConfigFromAppConfig } from "./config.js";
 import { checkMentionInTranscription } from "./mention.js";
+import { STTTranscriptionError, transcribe } from "./transcribe-core.js";
+import { mergeSttConfigFromAppConfig } from "./config.js";
 import { audioPreflightTranscribe } from "./preflight.js";
 //#region src/voice/stt/index.ts
 /**

package/dist/src/voice/stt/preflight.js

@@ -1,8 +1,8 @@
 import { createLogger } from "../../utils/logger/index.js";
 import { init_logger } from "../../utils/logger.js";
-import { transcribe } from "./transcribe-core.js";
 import { isSTTAvailable } from "./availability.js";
 import { checkMentionInTranscription } from "./mention.js";
+import { transcribe } from "./transcribe-core.js";
 //#region src/voice/stt/preflight.ts
 init_logger();
 const log = createLogger("STT:Preflight");

package/dist/src/voice/stt/providers/alibaba-transcription.js

@@ -1,14 +1,14 @@
 import { createLogger } from "../../../utils/logger/index.js";
 import { init_logger } from "../../../utils/logger.js";
-import { registerMediaUnderstandingProvider } from "../../../media-understanding/registry.js";
 import { postJsonRequest } from "../../../media-shared/http/provider-http.js";
 import "../../../media-shared/http/index.js";
+import { registerMediaUnderstandingProvider } from "../../../media-understanding/registry.js";
 import { openDashScopeStreamingStt } from "../../dashscope/streaming-stt-session.js";
 //#region src/voice/stt/providers/alibaba-transcription.ts
 init_logger();
 const log = createLogger("STT:Alibaba");
-const DEFAULT_MODEL = "qwen-audio-3.0-asr-flash";
-const DEFAULT_STREAMING_MODEL = "qwen-audio-3.0-asr-flash-streaming";
+const DEFAULT_MODEL = "qwen-audio-3.1-asr-flash";
+const DEFAULT_STREAMING_MODEL = "qwen-audio-3.1-asr-flash-streaming";
 const DEFAULT_BASE_URL = "https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation";
 function audioFormat(request) {
 	const extension = request.fileName.split(".").pop()?.toLowerCase();
@@ -92,7 +92,7 @@ const alibabaTranscriptionProvider = {
 		inputSampleRates: [16e3],
 		turnDetection: ["server_vad"],
 		defaultModel: DEFAULT_STREAMING_MODEL,
-		models: [DEFAULT_STREAMING_MODEL]
+		models: [DEFAULT_STREAMING_MODEL, "qwen-audio-3.0-asr-flash-streaming"]
 	},
 	openAudioStream: (request) => openDashScopeStreamingStt({
 		...request,

package/dist/src/voice/stt/providers/xopc-cloud-transcription.js

@@ -2,9 +2,9 @@ import { getModelCatalogStore, init_model_catalog_store } from "../../../provide
 import { init_xopc_cloud_config, resolveXopcModelRouterUrl } from "../../../providers/xopc-cloud-config.js";
 import { getProviderAuthService, init_provider_auth_service } from "../../../providers/provider-auth-service.js";
 import { compareCatalogModels } from "../../../providers/model-catalog-ranking.js";
-import { registerMediaUnderstandingProvider } from "../../../media-understanding/registry.js";
 import { openPlatformStt } from "../../platform-streams.js";
 import { platformVoiceModels, requirePlatformVoiceModel } from "../../platform-catalog.js";
+import { registerMediaUnderstandingProvider } from "../../../media-understanding/registry.js";
 //#region src/voice/stt/providers/xopc-cloud-transcription.ts
 init_model_catalog_store();
 init_provider_auth_service();

package/dist/src/voice/stt/transcribe-core.js

@@ -1,7 +1,7 @@
 import { createLogger } from "../../utils/logger/index.js";
 import { init_logger } from "../../utils/logger.js";
-import { runAudioTranscription } from "../../media-understanding/audio-transcription-runner.js";
 import { resolveSTTProviderChain } from "./factory.js";
+import { runAudioTranscription } from "../../media-understanding/audio-transcription-runner.js";
 //#region src/voice/stt/transcribe-core.ts
 init_logger();
 const log = createLogger("STT");

package/dist/src/voice/stt/types.js

@@ -3,7 +3,7 @@ const DEFAULT_STT_CONFIG = {
 	enabled: false,
 	provider: "openai",
 	providers: {
-		alibaba: { model: "qwen-audio-3.0-asr-flash" },
+		alibaba: { model: "qwen-audio-3.1-asr-flash" },
 		openai: { model: "gpt-4o-mini-transcribe" }
 	},
 	fallback: {

package/dist/src/voice/tts/index.js

@@ -4,12 +4,12 @@ import { alibabaSpeechProvider } from "./providers/alibaba-speech.js";
 import { edgeSpeechProvider } from "./providers/edge-speech.js";
 import { MINIMAX_TTS_MODELS, MINIMAX_TTS_VOICES, minimaxSpeechProvider } from "./providers/minimax-speech.js";
 import "./providers/index.js";
-import { buildTtsSystemPromptHint, hasTtsDirectives, parseTtsDirectives, stripTtsDirectives } from "./directives.js";
 import { getAvailableProviders, isProviderConfigured, isTTSAvailable, listRegisteredSpeechProviderIds, resolveProviderOrder, resolveSpeechProvider, resolveSpeechProviderChain } from "./factory.js";
-import { preprocessText } from "./preprocess.js";
-import { speak, speakStream, speakWithProvider } from "./speak-core.js";
 import { appendTtsReadinessNote, formatTtsSetupHint, mergeTtsConfigFromAppConfig } from "./merge-config.js";
 import { TTSService, getChannelOutputFormat, getSupportedChannels, isVoiceCompatibleChannel, shouldUseTTS } from "./service.js";
+import { buildTtsSystemPromptHint, hasTtsDirectives, parseTtsDirectives, stripTtsDirectives } from "./directives.js";
+import { preprocessText } from "./preprocess.js";
+import { speak, speakStream, speakWithProvider } from "./speak-core.js";
 import { recordTtsFailure, recordTtsSuccess, ttsStatusTracker } from "./status-tracker.js";
 import { isTtsEnabled, maybeApplyTtsToPayload, resolveTtsAutoMode } from "./payload.js";
 export { MINIMAX_TTS_MODELS, MINIMAX_TTS_VOICES, OPENAI_TTS_MODELS, OPENAI_TTS_VOICES, TTSService, alibabaSpeechProvider, appendTtsReadinessNote, buildTtsSystemPromptHint, edgeSpeechProvider, formatTtsSetupHint, getAvailableProviders, getChannelOutputFormat, getSpeechProvider, getSupportedChannels, hasTtsDirectives, isProviderConfigured, isTTSAvailable, isTtsEnabled, isVoiceCompatibleChannel, listRegisteredSpeechProviderIds, listSpeechProviders, maybeApplyTtsToPayload, mergeTtsConfigFromAppConfig, minimaxSpeechProvider, openAiSpeechProvider, parseTtsDirectives, preprocessText, recordTtsFailure, recordTtsSuccess, registerSpeechProvider, resolveProviderOrder, resolveSpeechProvider, resolveSpeechProviderChain, resolveTtsAutoMode, shouldUseTTS, speak, speakStream, speakWithProvider, stripTtsDirectives, ttsStatusTracker };

package/dist/src/voice/tts/merge-config.js

@@ -1,5 +1,5 @@
-import { isTTSAvailable } from "./factory.js";
 import { DEFAULT_TTS_CONFIG } from "./types.js";
+import { isTTSAvailable } from "./factory.js";
 //#region src/voice/tts/merge-config.ts
 /**
 * Merge persisted app config `tts` with defaults to a full {@link TTSConfig}

package/dist/src/voice/tts/payload.js

@@ -1,7 +1,7 @@
 import { createLogger } from "../../utils/logger/index.js";
 import { init_logger } from "../../utils/logger.js";
-import { speak } from "./speak-core.js";
 import { getChannelOutputFormat, shouldUseTTS } from "./service.js";
+import { speak } from "./speak-core.js";
 import { compressAudio } from "./audio.js";
 import { recordTtsFailure, recordTtsSuccess } from "./status-tracker.js";
 //#region src/voice/tts/payload.ts

package/dist/src/voice/tts/providers/alibaba-speech.js

@@ -5,6 +5,7 @@ import { fetchWithTimeoutGuarded, postJsonRequest } from "../../../media-shared/
 import "../../../media-shared/http/index.js";
 import { registerSpeechProvider } from "../speech-registry.js";
 import { openDashScopeStreamingTts } from "../../dashscope/streaming-tts-stream.js";
+import { alibabaVoicesForModel } from "./alibaba-voices.js";
 //#region src/voice/tts/providers/alibaba-speech.ts
 /**
 * Alibaba DashScope TTS provider (qwen-tts model).
@@ -29,21 +30,11 @@ import { openDashScopeStreamingTts } from "../../dashscope/streaming-tts-stream.
 init_logger();
 const log = createLogger("SpeechProvider:Alibaba");
 const DEFAULT_BASE_URL = "https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation";
-const DEFAULT_MODEL = "qwen-tts";
+const DEFAULT_MODEL = "qwen3-tts-flash";
 const ALIBABA_REALTIME_TTS_MODEL = "qwen3-tts-flash-realtime";
-const DEFAULT_VOICE = "longxiaochun";
+const DEFAULT_VOICE = "Cherry";
 const ENV_KEY = "DASHSCOPE_API_KEY";
 const MAX_TEXT_LENGTH = 512;
-const ALIBABA_VOICES = [
-	"Cherry",
-	"Ethan",
-	"Serena",
-	"Chelsie",
-	"longxiaochun",
-	"longxiaobai",
-	"longwan",
-	"longcheng"
-];
 function asObject(value) {
 	return typeof value === "object" && value !== null && !Array.isArray(value) ? value : void 0;
 }
@@ -104,10 +95,7 @@ const alibabaSpeechProvider = {
 	resolveConfig: (ctx) => normalizeConfig(ctx.rawConfig),
 	isConfigured: (ctx) => Boolean(resolveApiKey(readProviderConfig(ctx.providerConfig))),
 	parseDirectiveToken: parseDirectiveTokenInternal,
-	listVoices: async () => ALIBABA_VOICES.map((id) => ({
-		id,
-		name: id
-	})),
+	listVoices: async ({ providerConfig }) => alibabaVoicesForModel(typeof providerConfig?.model === "string" ? providerConfig.model : DEFAULT_MODEL),
 	synthesize: async (req) => {
 		const config = readProviderConfig(req.providerConfig);
 		const apiKey = resolveApiKey(config);

package/dist/src/voice/tts/providers/alibaba-voices.d.ts

@@ -0,0 +1,3 @@
+import type { SpeechVoiceOption } from '../speech-provider-types.js';
+export declare const alibabaTtsVoices: SpeechVoiceOption[];
+export declare function alibabaVoicesForModel(model: string): SpeechVoiceOption[];

package/dist/src/voice/tts/providers/alibaba-voices.js

@@ -0,0 +1,197 @@
+const alibabaTtsVoices = [
+	[
+		"Cherry",
+		"芊悦",
+		"female",
+		"阳光亲切",
+		"明亮、自然的年轻女声"
+	],
+	[
+		"Serena",
+		"苏瑶",
+		"female",
+		"温柔",
+		"柔和亲切的年轻女声"
+	],
+	[
+		"Ethan",
+		"晨煦",
+		"male",
+		"阳光活力",
+		"清朗温暖，略带北方口音"
+	],
+	[
+		"Chelsie",
+		"千雪",
+		"female",
+		"甜美",
+		"软糯娇俏的少女声线"
+	],
+	[
+		"Momo",
+		"茉兔",
+		"female",
+		"俏皮",
+		"爱撒娇、活泼有趣"
+	],
+	[
+		"Vivian",
+		"十三",
+		"female",
+		"傲娇",
+		"可爱、略带小暴躁"
+	],
+	[
+		"Moon",
+		"月白",
+		"male",
+		"帅气",
+		"率性清爽的男声"
+	],
+	[
+		"Maia",
+		"四月",
+		"female",
+		"知性温柔",
+		"知性而柔和"
+	],
+	[
+		"Kai",
+		"凯",
+		"male",
+		"舒缓",
+		"舒适、放松的男声"
+	],
+	[
+		"Nofish",
+		"不吃鱼",
+		"male",
+		"随性",
+		"略带不翘舌口音"
+	],
+	[
+		"Bella",
+		"萌宝",
+		"female",
+		"可爱",
+		"灵动俏皮的少女声"
+	],
+	[
+		"Jennifer",
+		"詹妮弗",
+		"female",
+		"电影质感",
+		"美式英语女声"
+	],
+	[
+		"Ryan",
+		"甜茶",
+		"male",
+		"戏剧感",
+		"富有节奏与张力"
+	],
+	[
+		"Katerina",
+		"卡捷琳娜",
+		"female",
+		"成熟",
+		"韵律丰富的成熟女声"
+	],
+	[
+		"Aiden",
+		"艾登",
+		"male",
+		"年轻",
+		"轻快的美式英语男声"
+	],
+	[
+		"Eldric Sage",
+		"沧明子",
+		"male",
+		"沉稳睿智",
+		"成熟老者声线"
+	],
+	[
+		"Mia",
+		"乖小妹",
+		"female",
+		"温顺",
+		"轻柔乖巧"
+	],
+	[
+		"Mochi",
+		"沙小弥",
+		"male",
+		"童真",
+		"聪明伶俐的少年声"
+	],
+	[
+		"Bellona",
+		"燕铮莺",
+		"female",
+		"豪迈",
+		"洪亮清晰、富有表现力"
+	],
+	[
+		"Vincent",
+		"田叔",
+		"male",
+		"沙哑",
+		"沧桑而豪迈的烟嗓"
+	],
+	[
+		"Neil",
+		"阿闻",
+		"male",
+		"播音",
+		"字正腔圆的新闻播报"
+	],
+	[
+		"Seren",
+		"小婉",
+		"female",
+		"舒缓",
+		"温和放松，适合睡前聆听"
+	],
+	[
+		"Andre",
+		"安德雷",
+		"male",
+		"磁性沉稳",
+		"自然舒适的成熟男声"
+	],
+	[
+		"Kiki",
+		"阿清",
+		"female",
+		"粤语甜美",
+		"活泼亲切的港式女声"
+	]
+].map(([id, name, gender, style, description]) => ({
+	id,
+	name: `${name} (${id})`,
+	gender,
+	style,
+	category: style,
+	description,
+	personalities: [style]
+}));
+function alibabaVoicesForModel(model) {
+	if (model === "qwen-tts" || model === "qwen-tts-realtime") return alibabaTtsVoices.filter((voice) => [
+		"Cherry",
+		"Serena",
+		"Ethan",
+		"Chelsie"
+	].includes(voice.id));
+	if (model.includes("instruct")) return alibabaTtsVoices.filter((voice) => ![
+		"Jennifer",
+		"Ryan",
+		"Katerina",
+		"Aiden",
+		"Andre",
+		"Kiki"
+	].includes(voice.id));
+	return alibabaTtsVoices;
+}
+//#endregion
+export { alibabaTtsVoices, alibabaVoicesForModel };

package/dist/src/voice/tts/providers/xopc-cloud-speech.js

@@ -2,9 +2,9 @@ import { getModelCatalogStore, init_model_catalog_store } from "../../../provide
 import { init_xopc_cloud_config, resolveXopcModelRouterUrl } from "../../../providers/xopc-cloud-config.js";
 import { getProviderAuthService, init_provider_auth_service } from "../../../providers/provider-auth-service.js";
 import { compareCatalogModels } from "../../../providers/model-catalog-ranking.js";
+import { registerSpeechProvider } from "../speech-registry.js";
 import { openPlatformTts } from "../../platform-streams.js";
 import { requirePlatformVoiceModel } from "../../platform-catalog.js";
-import { registerSpeechProvider } from "../speech-registry.js";
 //#region src/voice/tts/providers/xopc-cloud-speech.ts
 init_model_catalog_store();
 init_provider_auth_service();

package/dist/src/voice/tts/speak-core.js

@@ -1,7 +1,7 @@
 import { createLogger } from "../../utils/logger/index.js";
 import { init_logger } from "../../utils/logger.js";
-import { parseTtsDirectives } from "./directives.js";
 import { resolveSpeechProvider, resolveSpeechProviderChain } from "./factory.js";
+import { parseTtsDirectives } from "./directives.js";
 import { preprocessText } from "./preprocess.js";
 import { summarizeForTts } from "./summarize.js";
 //#region src/voice/tts/speak-core.ts

package/dist/src/voice/tts/speech-provider-types.d.ts

@@ -97,6 +97,7 @@ export interface SpeechVoiceOption {
     description?: string;
     locale?: string;
     gender?: string;
+    style?: string;
     /** Provider-defined personality / style tags. */
     personalities?: string[];
 }