From d4a1e9f5f67201f7a25960956ce97e20edfecdfa Mon Sep 17 00:00:00 2001
From: Neko Ayaka <neko@ayaka.moe>
Date: Fri, 18 Apr 2025 23:45:02 +0800
Subject: [PATCH] feat(stage-web|stage-tamagotchi): supports Alibaba Cloud
 Model Studio & Volcano Engine

---
 apps/stage-tamagotchi/locales/en.yml          |  11 ++
 apps/stage-tamagotchi/locales/zh-CN.yml       |  11 ++
 .../providers/alibaba-cloud-model-studio.vue  | 154 +++++++++++++++
 .../pages/settings/providers/elevenlabs.vue   | 153 ++++++++++++--
 .../settings/providers/microsoft-speech.vue   |   7 -
 .../pages/settings/providers/volcengine.vue   | 144 ++++++++++++++
 apps/stage-tamagotchi/src/styles/themes.css   |   2 +-
 apps/stage-web/locales/en.yml                 |  11 ++
 apps/stage-web/locales/zh-CN.yml              |  11 ++
 .../providers/alibaba-cloud-model-studio.vue  | 154 +++++++++++++++
 .../pages/settings/providers/elevenlabs.vue   | 153 ++++++++++++--
 .../settings/providers/microsoft-speech.vue   |   7 -
 .../pages/settings/providers/volcengine.vue   | 144 ++++++++++++++
 apps/stage-web/src/styles/themes.css          |   2 +-
 cspell.config.yaml                            |   7 +
 packages/stage-ui/package.json                |   1 +
 .../components/Providers/SpeechPlayground.vue |  24 ---
 .../Providers/SpeechProviderSettings.vue      |   5 +-
 .../Providers/SpeechVoiceSettings.vue         | 102 ----------
 .../src/components/Providers/index.ts         |   2 -
 packages/stage-ui/src/constants/elevenlabs.ts |  48 -----
 packages/stage-ui/src/constants/index.ts      |   1 -
 .../stage-ui/src/stores/fix/elevenlabs.ts     | 186 ------------------
 .../stage-ui/src/stores/fix/list-voices.ts    |  22 ---
 packages/stage-ui/src/stores/fix/microsoft.ts | 174 ----------------
 packages/stage-ui/src/stores/fix/voice.ts     |  41 ----
 .../stage-ui/src/stores/modules/speech.ts     |  27 +--
 packages/stage-ui/src/stores/providers.ts     | 126 +++++++++++-
 packages/stage-ui/src/stores/settings.ts      |   2 +-
 .../stories/ThemeColorsHueControl.vue         |   2 +-
 packages/stage-ui/stories/themes.css          |   2 +-
 pnpm-lock.yaml                                |  11 ++
 32 files changed, 1057 insertions(+), 690 deletions(-)
 create mode 100644 apps/stage-tamagotchi/src/pages/settings/providers/alibaba-cloud-model-studio.vue
 create mode 100644 apps/stage-tamagotchi/src/pages/settings/providers/volcengine.vue
 create mode 100644 apps/stage-web/src/pages/settings/providers/alibaba-cloud-model-studio.vue
 create mode 100644 apps/stage-web/src/pages/settings/providers/volcengine.vue
 delete mode 100644 packages/stage-ui/src/components/Providers/SpeechVoiceSettings.vue
 delete mode 100644 packages/stage-ui/src/constants/elevenlabs.ts
 delete mode 100644 packages/stage-ui/src/stores/fix/elevenlabs.ts
 delete mode 100644 packages/stage-ui/src/stores/fix/list-voices.ts
 delete mode 100644 packages/stage-ui/src/stores/fix/microsoft.ts
 delete mode 100644 packages/stage-ui/src/stores/fix/voice.ts

diff --git a/apps/stage-tamagotchi/locales/en.yml b/apps/stage-tamagotchi/locales/en.yml
index 489378307..23f566340 100644
--- a/apps/stage-tamagotchi/locales/en.yml
+++ b/apps/stage-tamagotchi/locales/en.yml
@@ -218,6 +218,9 @@ settings:
             title: Voice Settings
       description: LLMs, speech providers, etc.
       provider:
+        alibaba-cloud-model-studio:
+          description: bailian.console.aliyun.com
+          title: Alibaba Cloud Model Studio
         anthropic:
           description: anthropic.com
           title: Anthropic | Claude
@@ -326,6 +329,14 @@ settings:
         vllm:
           description: vllm.ai
           title: vLLM
+        volcengine:
+          description: volcengine.com
+          fields:
+            field:
+              appId:
+                description: App ID of the project where you can obtain in Console
+                label: App ID
+          title: Volcano Engine
         xai:
           description: x.ai
           title: xAI
diff --git a/apps/stage-tamagotchi/locales/zh-CN.yml b/apps/stage-tamagotchi/locales/zh-CN.yml
index 5039e739c..afe10c3e1 100644
--- a/apps/stage-tamagotchi/locales/zh-CN.yml
+++ b/apps/stage-tamagotchi/locales/zh-CN.yml
@@ -207,6 +207,9 @@ settings:
             title: 声音配置
       description: LLM，语音合成，语音识别提供商等
       provider:
+        alibaba-cloud-model-studio:
+          description: bailian.console.aliyun.com
+          title: 阿里百炼
         anthropic:
           description: anthropic.com
           title: Anthropic | Claude
@@ -313,6 +316,14 @@ settings:
         vllm:
           description: vllm.ai
           title: vLLM
+        volcengine:
+          description: volcengine.com
+          fields:
+            field:
+              appId:
+                description: 可在控制台获取的 App ID
+                label: App ID
+          title: 火山引擎
         xai:
           description: X.AI
           title: xAI
diff --git a/apps/stage-tamagotchi/src/pages/settings/providers/alibaba-cloud-model-studio.vue b/apps/stage-tamagotchi/src/pages/settings/providers/alibaba-cloud-model-studio.vue
new file mode 100644
index 000000000..55d0faac3
--- /dev/null
+++ b/apps/stage-tamagotchi/src/pages/settings/providers/alibaba-cloud-model-studio.vue
@@ -0,0 +1,154 @@
+<script setup lang="ts">
+import type { UnElevenLabsOptions } from '@xsai-ext/providers-local'
+import type { SpeechProviderWithExtraOptions } from '@xsai-ext/shared-providers'
+
+import {
+  FieldRange,
+  SpeechPlayground,
+  SpeechProviderSettings,
+} from '@proj-airi/stage-ui/components'
+import { useProvidersStore, useSpeechStore } from '@proj-airi/stage-ui/stores'
+import { storeToRefs } from 'pinia'
+import { computed, onMounted, ref, watch } from 'vue'
+import { useI18n } from 'vue-i18n'
+
+const providerId = 'alibaba-cloud-model-studio'
+const defaultModel = 'cosyvoice-v1'
+
+// Default voice settings specific to ElevenLabs
+const defaultVoiceSettings = {
+  speed: 1.0,
+}
+
+const pitch = ref<number>(0)
+const speed = ref<number>(1.0)
+const volume = ref<number>(0)
+
+const speechStore = useSpeechStore()
+const providersStore = useProvidersStore()
+const { providers } = storeToRefs(providersStore)
+const { t } = useI18n()
+
+// Check if API key is configured
+const apiKeyConfigured = computed(() => !!providers.value[providerId]?.apiKey)
+
+// Get available voices for ElevenLabs
+const availableVoices = computed(() => {
+  return speechStore.availableVoices[providerId] || []
+})
+
+// Generate speech with ElevenLabs-specific parameters
+async function handleGenerateSpeech(input: string, voiceId: string, _useSSML: boolean) {
+  const provider = providersStore.getProviderInstance(providerId) as SpeechProviderWithExtraOptions<string, UnElevenLabsOptions>
+  if (!provider) {
+    throw new Error('Failed to initialize speech provider')
+  }
+
+  // Get provider configuration
+  const providerConfig = providersStore.getProviderConfig(providerId)
+
+  // Get model from configuration or use default
+  const model = providerConfig.model as string | undefined || defaultModel
+
+  // ElevenLabs doesn't need SSML conversion, but if SSML is provided, use it directly
+  return await speechStore.speech(
+    provider,
+    model,
+    input,
+    voiceId,
+    {
+      ...providerConfig,
+      ...defaultVoiceSettings,
+    },
+  )
+}
+
+onMounted(async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  const providerMetadata = providersStore.getProviderMetadata(providerId)
+  if (await providerMetadata.validators.validateProviderConfig(providerConfig)) {
+    await speechStore.loadVoicesForProvider(providerId)
+  }
+  else {
+    console.error('Failed to validate provider config', providerConfig)
+  }
+})
+
+watch(pitch, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.pitch = pitch.value
+})
+
+watch(speed, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.speed = speed.value
+})
+
+watch(volume, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.volume = volume.value
+})
+
+watch(providers, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  const providerMetadata = providersStore.getProviderMetadata(providerId)
+  if (await providerMetadata.validators.validateProviderConfig(providerConfig)) {
+    await speechStore.loadVoicesForProvider(providerId)
+  }
+  else {
+    console.error('Failed to validate provider config', providerConfig)
+  }
+}, {
+  immediate: true,
+})
+</script>
+
+<template>
+  <SpeechProviderSettings
+    :provider-id="providerId"
+    :default-model="defaultModel"
+    :additional-settings="defaultVoiceSettings"
+  >
+    <!-- Voice settings specific to ElevenLabs -->
+    <template #voice-settings>
+      <div flex="~ col gap-4">
+        <!-- Pitch control - common to most providers -->
+        <FieldRange
+          v-model="pitch"
+          :label="t('settings.pages.providers.provider.common.fields.field.pitch.label')"
+          :description="t('settings.pages.providers.provider.common.fields.field.pitch.description')"
+          :min="-100"
+          :max="100" :step="1" :format-value="value => `${value}%`"
+        />
+
+        <!-- Speed control - common to most providers -->
+        <FieldRange
+          v-model="speed"
+          :label="t('settings.pages.providers.provider.common.fields.field.speed.label')"
+          :description="t('settings.pages.providers.provider.common.fields.field.speed.description')"
+          :min="0.5"
+          :max="2.0" :step="0.01"
+        />
+
+        <!-- Volume control - available in some providers -->
+        <FieldRange
+          v-model="volume"
+          :label="t('settings.pages.providers.provider.common.fields.field.volume.label')"
+          :description="t('settings.pages.providers.provider.common.fields.field.volume.description')"
+          :min="-100"
+          :max="100" :step="1" :format-value="value => `${value}%`"
+        />
+      </div>
+    </template>
+
+    <!-- Replace the default playground with our standalone component -->
+    <template #playground>
+      <SpeechPlayground
+        :available-voices="availableVoices"
+        :generate-speech="handleGenerateSpeech"
+        :api-key-configured="apiKeyConfigured"
+        default-text="Hello! This is a test of the ElevenLabs voice synthesis."
+      />
+    </template>
+  </SpeechProviderSettings>
+</template>
diff --git a/apps/stage-tamagotchi/src/pages/settings/providers/elevenlabs.vue b/apps/stage-tamagotchi/src/pages/settings/providers/elevenlabs.vue
index b991e51c9..e66eed0ba 100644
--- a/apps/stage-tamagotchi/src/pages/settings/providers/elevenlabs.vue
+++ b/apps/stage-tamagotchi/src/pages/settings/providers/elevenlabs.vue
@@ -3,13 +3,15 @@ import type { UnElevenLabsOptions } from '@xsai-ext/providers-local'
 import type { SpeechProviderWithExtraOptions } from '@xsai-ext/shared-providers'
 
 import {
+  FieldCheckbox,
+  FieldRange,
   SpeechPlayground,
   SpeechProviderSettings,
-  SpeechVoiceSettings,
 } from '@proj-airi/stage-ui/components'
 import { useProvidersStore, useSpeechStore } from '@proj-airi/stage-ui/stores'
 import { storeToRefs } from 'pinia'
-import { computed } from 'vue'
+import { computed, onMounted, ref, watch } from 'vue'
+import { useI18n } from 'vue-i18n'
 
 const providerId = 'elevenlabs'
 const defaultModel = 'eleven_multilingual_v2'
@@ -23,9 +25,18 @@ const defaultVoiceSettings = {
   useSpeakerBoost: true,
 }
 
+const pitch = ref<number>(0)
+const speed = ref<number>(1.0)
+const volume = ref<number>(0)
+const style = ref<number>(0)
+const stability = ref<number>(0.5)
+const similarityBoost = ref<number>(0.75)
+const useSpeakerBoost = ref<boolean>(false)
+
 const speechStore = useSpeechStore()
 const providersStore = useProvidersStore()
 const { providers } = storeToRefs(providersStore)
+const { t } = useI18n()
 
 // Check if API key is configured
 const apiKeyConfigured = computed(() => !!providers.value[providerId]?.apiKey)
@@ -35,11 +46,6 @@ const availableVoices = computed(() => {
   return speechStore.availableVoices[providerId] || []
 })
 
-// Get available languages
-const availableLanguages = computed(() => {
-  return speechStore.availableLanguages
-})
-
 // Generate speech with ElevenLabs-specific parameters
 async function handleGenerateSpeech(input: string, voiceId: string, _useSSML: boolean) {
   const provider = providersStore.getProviderInstance(providerId) as SpeechProviderWithExtraOptions<string, UnElevenLabsOptions>
@@ -65,6 +71,65 @@ async function handleGenerateSpeech(input: string, voiceId: string, _useSSML: bo
     },
   )
 }
+
+onMounted(async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  const providerMetadata = providersStore.getProviderMetadata(providerId)
+  if (await providerMetadata.validators.validateProviderConfig(providerConfig)) {
+    await speechStore.loadVoicesForProvider(providerId)
+  }
+  else {
+    console.error('Failed to validate provider config', providerConfig)
+  }
+})
+
+watch(pitch, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.pitch = pitch.value
+})
+
+watch(speed, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.speed = speed.value
+})
+
+watch(volume, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.volume = volume.value
+})
+
+watch(style, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.style = style.value
+})
+
+watch(stability, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.stability = stability.value
+})
+
+watch(similarityBoost, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.similarityBoost = similarityBoost.value
+})
+
+watch(useSpeakerBoost, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.useSpeakerBoost = useSpeakerBoost.value
+})
+
+watch(providers, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  const providerMetadata = providersStore.getProviderMetadata(providerId)
+  if (await providerMetadata.validators.validateProviderConfig(providerConfig)) {
+    await speechStore.loadVoicesForProvider(providerId)
+  }
+  else {
+    console.error('Failed to validate provider config', providerConfig)
+  }
+}, {
+  immediate: true,
+})
 </script>
 
 <template>
@@ -74,23 +139,75 @@ async function handleGenerateSpeech(input: string, voiceId: string, _useSSML: bo
     :additional-settings="defaultVoiceSettings"
   >
     <!-- Voice settings specific to ElevenLabs -->
-    <template #voice-settings="{ voiceSettings, updateVoiceSettings }">
-      <SpeechVoiceSettings
-        :settings="voiceSettings"
-        :show-similarity-boost="true"
-        :show-stability="true"
-        :show-speed="true"
-        :show-style="true"
-        :show-speaker-boost="true"
-        @update="updateVoiceSettings"
-      />
+    <template #voice-settings>
+      <div flex="~ col gap-4">
+        <!-- Pitch control - common to most providers -->
+        <FieldRange
+          v-model="pitch"
+          :label="t('settings.pages.providers.provider.common.fields.field.pitch.label')"
+          :description="t('settings.pages.providers.provider.common.fields.field.pitch.description')"
+          :min="-100"
+          :max="100" :step="1" :format-value="value => `${value}%`"
+        />
+
+        <!-- Speed control - common to most providers -->
+        <FieldRange
+          v-model="speed"
+          :label="t('settings.pages.providers.provider.common.fields.field.speed.label')"
+          :description="t('settings.pages.providers.provider.common.fields.field.speed.description')"
+          :min="0.5"
+          :max="2.0" :step="0.01"
+        />
+
+        <!-- Volume control - available in some providers -->
+        <FieldRange
+          v-model="volume"
+          :label="t('settings.pages.providers.provider.common.fields.field.volume.label')"
+          :description="t('settings.pages.providers.provider.common.fields.field.volume.description')"
+          :min="-100"
+          :max="100" :step="1" :format-value="value => `${value}%`"
+        />
+
+        <!-- Style control - specific to ElevenLabs -->
+        <FieldRange
+          v-model="style"
+          :label="t('settings.pages.providers.provider.elevenlabs.fields.field.style.label')"
+          :description="t('settings.pages.providers.provider.elevenlabs.fields.field.style.description')"
+          :min="0"
+          :max="1" :step="0.01"
+        />
+
+        <!-- Stability control - specific to ElevenLabs -->
+        <FieldRange
+          v-model="stability"
+          :label="t('settings.pages.providers.provider.elevenlabs.fields.field.stability.label')"
+          :description="t('settings.pages.providers.provider.elevenlabs.fields.field.stability.description')"
+          :min="0"
+          :max="1" :step="0.01"
+        />
+
+        <!-- Similarity Boost control - specific to ElevenLabs -->
+        <FieldRange
+          v-model="similarityBoost"
+          :label="t('settings.pages.providers.provider.elevenlabs.fields.field.simularity-boost.label')"
+          :description="t('settings.pages.providers.provider.elevenlabs.fields.field.simularity-boost.description')"
+          :min="0"
+          :max="1" :step="0.01"
+        />
+
+        <!-- Speaker Boost checkbox - specific to ElevenLabs -->
+        <FieldCheckbox
+          v-model="useSpeakerBoost"
+          :label="t('settings.pages.providers.provider.elevenlabs.fields.field.speaker-boost.label')"
+          :description="t('settings.pages.providers.provider.elevenlabs.fields.field.speaker-boost.description')"
+        />
+      </div>
     </template>
 
     <!-- Replace the default playground with our standalone component -->
     <template #playground>
       <SpeechPlayground
         :available-voices="availableVoices"
-        :available-languages="availableLanguages"
         :generate-speech="handleGenerateSpeech"
         :api-key-configured="apiKeyConfigured"
         default-text="Hello! This is a test of the ElevenLabs voice synthesis."
diff --git a/apps/stage-tamagotchi/src/pages/settings/providers/microsoft-speech.vue b/apps/stage-tamagotchi/src/pages/settings/providers/microsoft-speech.vue
index c8e8cb12b..cb7ad29ea 100644
--- a/apps/stage-tamagotchi/src/pages/settings/providers/microsoft-speech.vue
+++ b/apps/stage-tamagotchi/src/pages/settings/providers/microsoft-speech.vue
@@ -6,7 +6,6 @@ import {
   FieldInput,
   SpeechPlayground,
   SpeechProviderSettings,
-  SpeechVoiceSettings,
 } from '@proj-airi/stage-ui/components'
 import { useProvidersStore, useSpeechStore } from '@proj-airi/stage-ui/stores'
 import { storeToRefs } from 'pinia'
@@ -52,11 +51,6 @@ const availableVoices = computed(() => {
   return speechStore.availableVoices[providerId] || []
 })
 
-// Get available languages
-const availableLanguages = computed(() => {
-  return speechStore.availableLanguages
-})
-
 // Generate speech with Microsoft-specific parameters
 async function handleGenerateSpeech(input: string, voiceId: string, useSSML: boolean) {
   const provider = providersStore.getProviderInstance(providerId) as SpeechProviderWithExtraOptions<string, UnMicrosoftOptions>
@@ -143,7 +137,6 @@ async function handleGenerateSpeech(input: string, voiceId: string, useSSML: boo
     <template #playground>
       <SpeechPlayground
         :available-voices="availableVoices"
-        :available-languages="availableLanguages"
         :generate-speech="handleGenerateSpeech"
         :api-key-configured="apiKeyConfigured"
         default-text="Hello! This is a test of the Microsoft Speech synthesis."
diff --git a/apps/stage-tamagotchi/src/pages/settings/providers/volcengine.vue b/apps/stage-tamagotchi/src/pages/settings/providers/volcengine.vue
new file mode 100644
index 000000000..de814de91
--- /dev/null
+++ b/apps/stage-tamagotchi/src/pages/settings/providers/volcengine.vue
@@ -0,0 +1,144 @@
+<script setup lang="ts">
+import type { UnElevenLabsOptions } from '@xsai-ext/providers-local'
+import type { SpeechProviderWithExtraOptions } from '@xsai-ext/shared-providers'
+
+import {
+  FieldInput,
+  FieldRange,
+  SpeechPlayground,
+  SpeechProviderSettings,
+} from '@proj-airi/stage-ui/components'
+import { useProvidersStore, useSpeechStore } from '@proj-airi/stage-ui/stores'
+import { storeToRefs } from 'pinia'
+import { computed, onMounted, ref, watch } from 'vue'
+import { useI18n } from 'vue-i18n'
+
+const providerId = 'volcengine'
+const defaultModel = 'v1'
+
+const speedRatio = ref<number>(1.0)
+
+const speechStore = useSpeechStore()
+const providersStore = useProvidersStore()
+const { providers } = storeToRefs(providersStore)
+const { t } = useI18n()
+
+// Additional settings specific to Volcengine (appId)
+const appId = computed({
+  get: () => (providers.value[providerId]?.app as any)?.appId as string | undefined || '',
+  set: (value) => {
+    if (!providers.value[providerId])
+      providers.value[providerId] = {}
+
+    providers.value[providerId].app = {
+      appId: value,
+    }
+  },
+})
+
+// Check if API key is configured
+const apiKeyConfigured = computed(() => !!providers.value[providerId]?.apiKey)
+
+// Get available voices for ElevenLabs
+const availableVoices = computed(() => {
+  return speechStore.availableVoices[providerId] || []
+})
+
+// Generate speech with ElevenLabs-specific parameters
+async function handleGenerateSpeech(input: string, voiceId: string, _useSSML: boolean) {
+  const provider = providersStore.getProviderInstance(providerId) as SpeechProviderWithExtraOptions<string, UnElevenLabsOptions>
+  if (!provider) {
+    throw new Error('Failed to initialize speech provider')
+  }
+
+  // Get provider configuration
+  const providerConfig = providersStore.getProviderConfig(providerId)
+
+  // Get model from configuration or use default
+  const model = providerConfig.model as string | undefined || defaultModel
+
+  // ElevenLabs doesn't need SSML conversion, but if SSML is provided, use it directly
+  return await speechStore.speech(
+    provider,
+    model,
+    input,
+    voiceId,
+    {
+      ...providerConfig,
+    },
+  )
+}
+
+onMounted(async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  const providerMetadata = providersStore.getProviderMetadata(providerId)
+  if (await providerMetadata.validators.validateProviderConfig(providerConfig)) {
+    await speechStore.loadVoicesForProvider(providerId)
+  }
+  else {
+    console.error('Failed to validate provider config', providerConfig)
+  }
+})
+
+watch(speedRatio, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  if (!providerConfig.audio) {
+    providerConfig.audio = {}
+  }
+
+  (providerConfig.audio as any).speedRatio = speedRatio.value
+})
+
+watch([providers, appId], async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  const providerMetadata = providersStore.getProviderMetadata(providerId)
+  if (await providerMetadata.validators.validateProviderConfig(providerConfig)) {
+    await speechStore.loadVoicesForProvider(providerId)
+  }
+  else {
+    console.error('Failed to validate provider config', providerConfig)
+  }
+}, {
+  immediate: true,
+})
+</script>
+
+<template>
+  <SpeechProviderSettings
+    :provider-id="providerId"
+    :default-model="defaultModel"
+  >
+    <!-- Voice settings specific to ElevenLabs -->
+    <template #basic-settings>
+      <div flex="~ col gap-4">
+        <FieldInput
+          v-model="appId"
+          :label="t('settings.pages.providers.provider.volcengine.fields.field.appId.label')"
+          :description="t('settings.pages.providers.provider.volcengine.fields.field.appId.description')"
+          required
+        />
+      </div>
+    </template>
+
+    <template #voice-settings>
+      <!-- Speed control - common to most providers -->
+      <FieldRange
+        v-model="speedRatio"
+        :label="t('settings.pages.providers.provider.common.fields.field.speed.label')"
+        :description="t('settings.pages.providers.provider.common.fields.field.speed.description')"
+        :min="0.5"
+        :max="2.0" :step="0.01"
+      />
+    </template>
+
+    <!-- Replace the default playground with our standalone component -->
+    <template #playground>
+      <SpeechPlayground
+        :available-voices="availableVoices"
+        :generate-speech="handleGenerateSpeech"
+        :api-key-configured="apiKeyConfigured"
+        default-text="Hello! This is a test of the ElevenLabs voice synthesis."
+      />
+    </template>
+  </SpeechProviderSettings>
+</template>
diff --git a/apps/stage-tamagotchi/src/styles/themes.css b/apps/stage-tamagotchi/src/styles/themes.css
index 638ccb141..47b046667 100644
--- a/apps/stage-tamagotchi/src/styles/themes.css
+++ b/apps/stage-tamagotchi/src/styles/themes.css
@@ -11,7 +11,7 @@
   --airi-theme-primary-900: #8e0d3b;
   --airi-theme-primary-950: #50011b;
 
-  --theme-colors-hue: 354.31;
+  --theme-colors-hue: 220.44;
   --theme-colors-chroma: calc(0.18 + (cos(var(--theme-colors-hue) * 3.14159265 / 180) * 0.04));
   --theme-colors-chroma-50: calc(var(--theme-colors-chroma) * 0.3);
   --theme-colors-chroma-100: calc(var(--theme-colors-chroma) * 0.5);
diff --git a/apps/stage-web/locales/en.yml b/apps/stage-web/locales/en.yml
index d6d688617..86a5db1d6 100644
--- a/apps/stage-web/locales/en.yml
+++ b/apps/stage-web/locales/en.yml
@@ -227,6 +227,9 @@ settings:
             title: Voice Settings
       description: LLMs, speech providers, etc.
       provider:
+        alibaba-cloud-model-studio:
+          description: bailian.console.aliyun.com
+          title: Alibaba Cloud Model Studio
         anthropic:
           description: anthropic.com
           title: Anthropic | Claude
@@ -335,6 +338,14 @@ settings:
         vllm:
           description: vllm.ai
           title: vLLM
+        volcengine:
+          description: volcengine.com
+          fields:
+            field:
+              appId:
+                description: App ID of the project where you can obtain in Console
+                label: App ID
+          title: Volcano Engine
         xai:
           description: x.ai
           title: xAI
diff --git a/apps/stage-web/locales/zh-CN.yml b/apps/stage-web/locales/zh-CN.yml
index 79cba343a..73c0416a5 100644
--- a/apps/stage-web/locales/zh-CN.yml
+++ b/apps/stage-web/locales/zh-CN.yml
@@ -213,6 +213,9 @@ settings:
             title: 声音配置
       description: LLM，语音合成，语音识别提供商等
       provider:
+        alibaba-cloud-model-studio:
+          description: bailian.console.aliyun.com
+          title: 阿里百炼
         anthropic:
           description: anthropic.com
           title: Anthropic | Claude
@@ -319,6 +322,14 @@ settings:
         vllm:
           description: vllm.ai
           title: vLLM
+        volcengine:
+          description: volcengine.com
+          fields:
+            field:
+              appId:
+                description: 可在控制台获取的 App ID
+                label: App ID
+          title: 火山引擎
         xai:
           description: X.AI
           title: xAI
diff --git a/apps/stage-web/src/pages/settings/providers/alibaba-cloud-model-studio.vue b/apps/stage-web/src/pages/settings/providers/alibaba-cloud-model-studio.vue
new file mode 100644
index 000000000..55d0faac3
--- /dev/null
+++ b/apps/stage-web/src/pages/settings/providers/alibaba-cloud-model-studio.vue
@@ -0,0 +1,154 @@
+<script setup lang="ts">
+import type { UnElevenLabsOptions } from '@xsai-ext/providers-local'
+import type { SpeechProviderWithExtraOptions } from '@xsai-ext/shared-providers'
+
+import {
+  FieldRange,
+  SpeechPlayground,
+  SpeechProviderSettings,
+} from '@proj-airi/stage-ui/components'
+import { useProvidersStore, useSpeechStore } from '@proj-airi/stage-ui/stores'
+import { storeToRefs } from 'pinia'
+import { computed, onMounted, ref, watch } from 'vue'
+import { useI18n } from 'vue-i18n'
+
+const providerId = 'alibaba-cloud-model-studio'
+const defaultModel = 'cosyvoice-v1'
+
+// Default voice settings specific to ElevenLabs
+const defaultVoiceSettings = {
+  speed: 1.0,
+}
+
+const pitch = ref<number>(0)
+const speed = ref<number>(1.0)
+const volume = ref<number>(0)
+
+const speechStore = useSpeechStore()
+const providersStore = useProvidersStore()
+const { providers } = storeToRefs(providersStore)
+const { t } = useI18n()
+
+// Check if API key is configured
+const apiKeyConfigured = computed(() => !!providers.value[providerId]?.apiKey)
+
+// Get available voices for ElevenLabs
+const availableVoices = computed(() => {
+  return speechStore.availableVoices[providerId] || []
+})
+
+// Generate speech with ElevenLabs-specific parameters
+async function handleGenerateSpeech(input: string, voiceId: string, _useSSML: boolean) {
+  const provider = providersStore.getProviderInstance(providerId) as SpeechProviderWithExtraOptions<string, UnElevenLabsOptions>
+  if (!provider) {
+    throw new Error('Failed to initialize speech provider')
+  }
+
+  // Get provider configuration
+  const providerConfig = providersStore.getProviderConfig(providerId)
+
+  // Get model from configuration or use default
+  const model = providerConfig.model as string | undefined || defaultModel
+
+  // ElevenLabs doesn't need SSML conversion, but if SSML is provided, use it directly
+  return await speechStore.speech(
+    provider,
+    model,
+    input,
+    voiceId,
+    {
+      ...providerConfig,
+      ...defaultVoiceSettings,
+    },
+  )
+}
+
+onMounted(async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  const providerMetadata = providersStore.getProviderMetadata(providerId)
+  if (await providerMetadata.validators.validateProviderConfig(providerConfig)) {
+    await speechStore.loadVoicesForProvider(providerId)
+  }
+  else {
+    console.error('Failed to validate provider config', providerConfig)
+  }
+})
+
+watch(pitch, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.pitch = pitch.value
+})
+
+watch(speed, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.speed = speed.value
+})
+
+watch(volume, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.volume = volume.value
+})
+
+watch(providers, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  const providerMetadata = providersStore.getProviderMetadata(providerId)
+  if (await providerMetadata.validators.validateProviderConfig(providerConfig)) {
+    await speechStore.loadVoicesForProvider(providerId)
+  }
+  else {
+    console.error('Failed to validate provider config', providerConfig)
+  }
+}, {
+  immediate: true,
+})
+</script>
+
+<template>
+  <SpeechProviderSettings
+    :provider-id="providerId"
+    :default-model="defaultModel"
+    :additional-settings="defaultVoiceSettings"
+  >
+    <!-- Voice settings specific to ElevenLabs -->
+    <template #voice-settings>
+      <div flex="~ col gap-4">
+        <!-- Pitch control - common to most providers -->
+        <FieldRange
+          v-model="pitch"
+          :label="t('settings.pages.providers.provider.common.fields.field.pitch.label')"
+          :description="t('settings.pages.providers.provider.common.fields.field.pitch.description')"
+          :min="-100"
+          :max="100" :step="1" :format-value="value => `${value}%`"
+        />
+
+        <!-- Speed control - common to most providers -->
+        <FieldRange
+          v-model="speed"
+          :label="t('settings.pages.providers.provider.common.fields.field.speed.label')"
+          :description="t('settings.pages.providers.provider.common.fields.field.speed.description')"
+          :min="0.5"
+          :max="2.0" :step="0.01"
+        />
+
+        <!-- Volume control - available in some providers -->
+        <FieldRange
+          v-model="volume"
+          :label="t('settings.pages.providers.provider.common.fields.field.volume.label')"
+          :description="t('settings.pages.providers.provider.common.fields.field.volume.description')"
+          :min="-100"
+          :max="100" :step="1" :format-value="value => `${value}%`"
+        />
+      </div>
+    </template>
+
+    <!-- Replace the default playground with our standalone component -->
+    <template #playground>
+      <SpeechPlayground
+        :available-voices="availableVoices"
+        :generate-speech="handleGenerateSpeech"
+        :api-key-configured="apiKeyConfigured"
+        default-text="Hello! This is a test of the ElevenLabs voice synthesis."
+      />
+    </template>
+  </SpeechProviderSettings>
+</template>
diff --git a/apps/stage-web/src/pages/settings/providers/elevenlabs.vue b/apps/stage-web/src/pages/settings/providers/elevenlabs.vue
index b991e51c9..e66eed0ba 100644
--- a/apps/stage-web/src/pages/settings/providers/elevenlabs.vue
+++ b/apps/stage-web/src/pages/settings/providers/elevenlabs.vue
@@ -3,13 +3,15 @@ import type { UnElevenLabsOptions } from '@xsai-ext/providers-local'
 import type { SpeechProviderWithExtraOptions } from '@xsai-ext/shared-providers'
 
 import {
+  FieldCheckbox,
+  FieldRange,
   SpeechPlayground,
   SpeechProviderSettings,
-  SpeechVoiceSettings,
 } from '@proj-airi/stage-ui/components'
 import { useProvidersStore, useSpeechStore } from '@proj-airi/stage-ui/stores'
 import { storeToRefs } from 'pinia'
-import { computed } from 'vue'
+import { computed, onMounted, ref, watch } from 'vue'
+import { useI18n } from 'vue-i18n'
 
 const providerId = 'elevenlabs'
 const defaultModel = 'eleven_multilingual_v2'
@@ -23,9 +25,18 @@ const defaultVoiceSettings = {
   useSpeakerBoost: true,
 }
 
+const pitch = ref<number>(0)
+const speed = ref<number>(1.0)
+const volume = ref<number>(0)
+const style = ref<number>(0)
+const stability = ref<number>(0.5)
+const similarityBoost = ref<number>(0.75)
+const useSpeakerBoost = ref<boolean>(false)
+
 const speechStore = useSpeechStore()
 const providersStore = useProvidersStore()
 const { providers } = storeToRefs(providersStore)
+const { t } = useI18n()
 
 // Check if API key is configured
 const apiKeyConfigured = computed(() => !!providers.value[providerId]?.apiKey)
@@ -35,11 +46,6 @@ const availableVoices = computed(() => {
   return speechStore.availableVoices[providerId] || []
 })
 
-// Get available languages
-const availableLanguages = computed(() => {
-  return speechStore.availableLanguages
-})
-
 // Generate speech with ElevenLabs-specific parameters
 async function handleGenerateSpeech(input: string, voiceId: string, _useSSML: boolean) {
   const provider = providersStore.getProviderInstance(providerId) as SpeechProviderWithExtraOptions<string, UnElevenLabsOptions>
@@ -65,6 +71,65 @@ async function handleGenerateSpeech(input: string, voiceId: string, _useSSML: bo
     },
   )
 }
+
+onMounted(async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  const providerMetadata = providersStore.getProviderMetadata(providerId)
+  if (await providerMetadata.validators.validateProviderConfig(providerConfig)) {
+    await speechStore.loadVoicesForProvider(providerId)
+  }
+  else {
+    console.error('Failed to validate provider config', providerConfig)
+  }
+})
+
+watch(pitch, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.pitch = pitch.value
+})
+
+watch(speed, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.speed = speed.value
+})
+
+watch(volume, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.volume = volume.value
+})
+
+watch(style, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.style = style.value
+})
+
+watch(stability, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.stability = stability.value
+})
+
+watch(similarityBoost, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.similarityBoost = similarityBoost.value
+})
+
+watch(useSpeakerBoost, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  providerConfig.useSpeakerBoost = useSpeakerBoost.value
+})
+
+watch(providers, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  const providerMetadata = providersStore.getProviderMetadata(providerId)
+  if (await providerMetadata.validators.validateProviderConfig(providerConfig)) {
+    await speechStore.loadVoicesForProvider(providerId)
+  }
+  else {
+    console.error('Failed to validate provider config', providerConfig)
+  }
+}, {
+  immediate: true,
+})
 </script>
 
 <template>
@@ -74,23 +139,75 @@ async function handleGenerateSpeech(input: string, voiceId: string, _useSSML: bo
     :additional-settings="defaultVoiceSettings"
   >
     <!-- Voice settings specific to ElevenLabs -->
-    <template #voice-settings="{ voiceSettings, updateVoiceSettings }">
-      <SpeechVoiceSettings
-        :settings="voiceSettings"
-        :show-similarity-boost="true"
-        :show-stability="true"
-        :show-speed="true"
-        :show-style="true"
-        :show-speaker-boost="true"
-        @update="updateVoiceSettings"
-      />
+    <template #voice-settings>
+      <div flex="~ col gap-4">
+        <!-- Pitch control - common to most providers -->
+        <FieldRange
+          v-model="pitch"
+          :label="t('settings.pages.providers.provider.common.fields.field.pitch.label')"
+          :description="t('settings.pages.providers.provider.common.fields.field.pitch.description')"
+          :min="-100"
+          :max="100" :step="1" :format-value="value => `${value}%`"
+        />
+
+        <!-- Speed control - common to most providers -->
+        <FieldRange
+          v-model="speed"
+          :label="t('settings.pages.providers.provider.common.fields.field.speed.label')"
+          :description="t('settings.pages.providers.provider.common.fields.field.speed.description')"
+          :min="0.5"
+          :max="2.0" :step="0.01"
+        />
+
+        <!-- Volume control - available in some providers -->
+        <FieldRange
+          v-model="volume"
+          :label="t('settings.pages.providers.provider.common.fields.field.volume.label')"
+          :description="t('settings.pages.providers.provider.common.fields.field.volume.description')"
+          :min="-100"
+          :max="100" :step="1" :format-value="value => `${value}%`"
+        />
+
+        <!-- Style control - specific to ElevenLabs -->
+        <FieldRange
+          v-model="style"
+          :label="t('settings.pages.providers.provider.elevenlabs.fields.field.style.label')"
+          :description="t('settings.pages.providers.provider.elevenlabs.fields.field.style.description')"
+          :min="0"
+          :max="1" :step="0.01"
+        />
+
+        <!-- Stability control - specific to ElevenLabs -->
+        <FieldRange
+          v-model="stability"
+          :label="t('settings.pages.providers.provider.elevenlabs.fields.field.stability.label')"
+          :description="t('settings.pages.providers.provider.elevenlabs.fields.field.stability.description')"
+          :min="0"
+          :max="1" :step="0.01"
+        />
+
+        <!-- Similarity Boost control - specific to ElevenLabs -->
+        <FieldRange
+          v-model="similarityBoost"
+          :label="t('settings.pages.providers.provider.elevenlabs.fields.field.simularity-boost.label')"
+          :description="t('settings.pages.providers.provider.elevenlabs.fields.field.simularity-boost.description')"
+          :min="0"
+          :max="1" :step="0.01"
+        />
+
+        <!-- Speaker Boost checkbox - specific to ElevenLabs -->
+        <FieldCheckbox
+          v-model="useSpeakerBoost"
+          :label="t('settings.pages.providers.provider.elevenlabs.fields.field.speaker-boost.label')"
+          :description="t('settings.pages.providers.provider.elevenlabs.fields.field.speaker-boost.description')"
+        />
+      </div>
     </template>
 
     <!-- Replace the default playground with our standalone component -->
     <template #playground>
       <SpeechPlayground
         :available-voices="availableVoices"
-        :available-languages="availableLanguages"
         :generate-speech="handleGenerateSpeech"
         :api-key-configured="apiKeyConfigured"
         default-text="Hello! This is a test of the ElevenLabs voice synthesis."
diff --git a/apps/stage-web/src/pages/settings/providers/microsoft-speech.vue b/apps/stage-web/src/pages/settings/providers/microsoft-speech.vue
index c8e8cb12b..cb7ad29ea 100644
--- a/apps/stage-web/src/pages/settings/providers/microsoft-speech.vue
+++ b/apps/stage-web/src/pages/settings/providers/microsoft-speech.vue
@@ -6,7 +6,6 @@ import {
   FieldInput,
   SpeechPlayground,
   SpeechProviderSettings,
-  SpeechVoiceSettings,
 } from '@proj-airi/stage-ui/components'
 import { useProvidersStore, useSpeechStore } from '@proj-airi/stage-ui/stores'
 import { storeToRefs } from 'pinia'
@@ -52,11 +51,6 @@ const availableVoices = computed(() => {
   return speechStore.availableVoices[providerId] || []
 })
 
-// Get available languages
-const availableLanguages = computed(() => {
-  return speechStore.availableLanguages
-})
-
 // Generate speech with Microsoft-specific parameters
 async function handleGenerateSpeech(input: string, voiceId: string, useSSML: boolean) {
   const provider = providersStore.getProviderInstance(providerId) as SpeechProviderWithExtraOptions<string, UnMicrosoftOptions>
@@ -143,7 +137,6 @@ async function handleGenerateSpeech(input: string, voiceId: string, useSSML: boo
     <template #playground>
       <SpeechPlayground
         :available-voices="availableVoices"
-        :available-languages="availableLanguages"
         :generate-speech="handleGenerateSpeech"
         :api-key-configured="apiKeyConfigured"
         default-text="Hello! This is a test of the Microsoft Speech synthesis."
diff --git a/apps/stage-web/src/pages/settings/providers/volcengine.vue b/apps/stage-web/src/pages/settings/providers/volcengine.vue
new file mode 100644
index 000000000..de814de91
--- /dev/null
+++ b/apps/stage-web/src/pages/settings/providers/volcengine.vue
@@ -0,0 +1,144 @@
+<script setup lang="ts">
+import type { UnElevenLabsOptions } from '@xsai-ext/providers-local'
+import type { SpeechProviderWithExtraOptions } from '@xsai-ext/shared-providers'
+
+import {
+  FieldInput,
+  FieldRange,
+  SpeechPlayground,
+  SpeechProviderSettings,
+} from '@proj-airi/stage-ui/components'
+import { useProvidersStore, useSpeechStore } from '@proj-airi/stage-ui/stores'
+import { storeToRefs } from 'pinia'
+import { computed, onMounted, ref, watch } from 'vue'
+import { useI18n } from 'vue-i18n'
+
+const providerId = 'volcengine'
+const defaultModel = 'v1'
+
+const speedRatio = ref<number>(1.0)
+
+const speechStore = useSpeechStore()
+const providersStore = useProvidersStore()
+const { providers } = storeToRefs(providersStore)
+const { t } = useI18n()
+
+// Additional settings specific to Volcengine (appId)
+const appId = computed({
+  get: () => (providers.value[providerId]?.app as any)?.appId as string | undefined || '',
+  set: (value) => {
+    if (!providers.value[providerId])
+      providers.value[providerId] = {}
+
+    providers.value[providerId].app = {
+      appId: value,
+    }
+  },
+})
+
+// Check if API key is configured
+const apiKeyConfigured = computed(() => !!providers.value[providerId]?.apiKey)
+
+// Get available voices for ElevenLabs
+const availableVoices = computed(() => {
+  return speechStore.availableVoices[providerId] || []
+})
+
+// Generate speech with ElevenLabs-specific parameters
+async function handleGenerateSpeech(input: string, voiceId: string, _useSSML: boolean) {
+  const provider = providersStore.getProviderInstance(providerId) as SpeechProviderWithExtraOptions<string, UnElevenLabsOptions>
+  if (!provider) {
+    throw new Error('Failed to initialize speech provider')
+  }
+
+  // Get provider configuration
+  const providerConfig = providersStore.getProviderConfig(providerId)
+
+  // Get model from configuration or use default
+  const model = providerConfig.model as string | undefined || defaultModel
+
+  // ElevenLabs doesn't need SSML conversion, but if SSML is provided, use it directly
+  return await speechStore.speech(
+    provider,
+    model,
+    input,
+    voiceId,
+    {
+      ...providerConfig,
+    },
+  )
+}
+
+onMounted(async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  const providerMetadata = providersStore.getProviderMetadata(providerId)
+  if (await providerMetadata.validators.validateProviderConfig(providerConfig)) {
+    await speechStore.loadVoicesForProvider(providerId)
+  }
+  else {
+    console.error('Failed to validate provider config', providerConfig)
+  }
+})
+
+watch(speedRatio, async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  if (!providerConfig.audio) {
+    providerConfig.audio = {}
+  }
+
+  (providerConfig.audio as any).speedRatio = speedRatio.value
+})
+
+watch([providers, appId], async () => {
+  const providerConfig = providersStore.getProviderConfig(providerId)
+  const providerMetadata = providersStore.getProviderMetadata(providerId)
+  if (await providerMetadata.validators.validateProviderConfig(providerConfig)) {
+    await speechStore.loadVoicesForProvider(providerId)
+  }
+  else {
+    console.error('Failed to validate provider config', providerConfig)
+  }
+}, {
+  immediate: true,
+})
+</script>
+
+<template>
+  <SpeechProviderSettings
+    :provider-id="providerId"
+    :default-model="defaultModel"
+  >
+    <!-- Voice settings specific to ElevenLabs -->
+    <template #basic-settings>
+      <div flex="~ col gap-4">
+        <FieldInput
+          v-model="appId"
+          :label="t('settings.pages.providers.provider.volcengine.fields.field.appId.label')"
+          :description="t('settings.pages.providers.provider.volcengine.fields.field.appId.description')"
+          required
+        />
+      </div>
+    </template>
+
+    <template #voice-settings>
+      <!-- Speed control - common to most providers -->
+      <FieldRange
+        v-model="speedRatio"
+        :label="t('settings.pages.providers.provider.common.fields.field.speed.label')"
+        :description="t('settings.pages.providers.provider.common.fields.field.speed.description')"
+        :min="0.5"
+        :max="2.0" :step="0.01"
+      />
+    </template>
+
+    <!-- Replace the default playground with our standalone component -->
+    <template #playground>
+      <SpeechPlayground
+        :available-voices="availableVoices"
+        :generate-speech="handleGenerateSpeech"
+        :api-key-configured="apiKeyConfigured"
+        default-text="Hello! This is a test of the ElevenLabs voice synthesis."
+      />
+    </template>
+  </SpeechProviderSettings>
+</template>
diff --git a/apps/stage-web/src/styles/themes.css b/apps/stage-web/src/styles/themes.css
index 638ccb141..47b046667 100644
--- a/apps/stage-web/src/styles/themes.css
+++ b/apps/stage-web/src/styles/themes.css
@@ -11,7 +11,7 @@
   --airi-theme-primary-900: #8e0d3b;
   --airi-theme-primary-950: #50011b;
 
-  --theme-colors-hue: 354.31;
+  --theme-colors-hue: 220.44;
   --theme-colors-chroma: calc(0.18 + (cos(var(--theme-colors-hue) * 3.14159265 / 180) * 0.04));
   --theme-colors-chroma-50: calc(var(--theme-colors-chroma) * 0.3);
   --theme-colors-chroma-100: calc(var(--theme-colors-chroma) * 0.5);
diff --git a/cspell.config.yaml b/cspell.config.yaml
index 3af07203f..5e8c6ee53 100644
--- a/cspell.config.yaml
+++ b/cspell.config.yaml
@@ -8,6 +8,8 @@ words:
   - airi
   - airi-vtuber
   - Alaya
+  - alibabacloud
+  - aliyun
   - APNG
   - astrojs
   - Attributify
@@ -16,6 +18,7 @@ words:
   - Ayaka
   - baichuan
   - baiducloud
+  - bailian
   - bigserial
   - Bitstream
   - browserbasehq
@@ -26,6 +29,8 @@ words:
   - collectblock
   - composables
   - cooldown
+  - cosyvoice
+  - cozyvoice
   - crossws
   - csmmap
   - csmvector
@@ -158,11 +163,13 @@ words:
   - unhead
   - unocss
   - unplugin
+  - unspeech
   - valibot
   - vaul
   - velin
   - VITE
   - vllm
+  - Volcengine
   - vrma
   - vueuse
   - wavefile
diff --git a/packages/stage-ui/package.json b/packages/stage-ui/package.json
index c81f6b2be..c45ba4dd9 100644
--- a/packages/stage-ui/package.json
+++ b/packages/stage-ui/package.json
@@ -65,6 +65,7 @@
     "radix-vue": "^1.9.17",
     "reka-ui": "^2.2.0",
     "unist-builder": "^4.0.0",
+    "unspeech": "^0.1.7",
     "xast-util-to-xml": "^4.0.0",
     "xastscript": "^4.0.0"
   },
diff --git a/packages/stage-ui/src/components/Providers/SpeechPlayground.vue b/packages/stage-ui/src/components/Providers/SpeechPlayground.vue
index 50c687c44..49094eda1 100644
--- a/packages/stage-ui/src/components/Providers/SpeechPlayground.vue
+++ b/packages/stage-ui/src/components/Providers/SpeechPlayground.vue
@@ -10,7 +10,6 @@ const props = defineProps<{
   // Input fields
   defaultText?: string
   availableVoices: VoiceInfo[]
-  availableLanguages: string[]
 
   // Provider-specific handlers (provided from parent)
   generateSpeech: (input: string, voice: string, useSSML: boolean) => Promise<ArrayBuffer>
@@ -29,7 +28,6 @@ const errorMessage = ref('')
 const audioPlayer = ref<HTMLAudioElement | null>(null)
 const useSSML = ref(false)
 const ssmlText = ref('')
-const selectedLanguage = ref(props.availableLanguages[0] || 'en-US')
 const selectedVoice = ref('')
 
 // Watch for changes in available voices
@@ -106,7 +104,6 @@ defineExpose({
   testText,
   ssmlText,
   useSSML,
-  selectedLanguage,
   selectedVoice,
   isGenerating,
   audioUrl,
@@ -156,27 +153,6 @@ defineExpose({
       </template>
 
       <div flex="~ col gap-6">
-        <label grid="~ cols-2 gap-4">
-          <div>
-            <div class="flex items-center gap-1 text-sm font-medium">
-              {{ t('settings.pages.providers.provider.elevenlabs.playground.fields.field.language.label') }}
-            </div>
-            <div class="text-xs text-neutral-500 dark:text-neutral-400">
-              {{ t('settings.pages.providers.provider.elevenlabs.playground.fields.field.language.description') }}
-            </div>
-          </div>
-          <select
-            v-model="selectedLanguage"
-            border="neutral-300 dark:neutral-800 solid 2 focus:neutral-400 dark:focus:neutral-600"
-            transition="border duration-250 ease-in-out" w-full rounded-lg px-2 py-1 text-nowrap text-sm
-            outline-none
-          >
-            <option v-for="language in availableLanguages" :key="language" :value="language">
-              {{ language }}
-            </option>
-          </select>
-        </label>
-
         <label grid="~ cols-2 gap-4">
           <div>
             <div class="flex items-center gap-1 text-sm font-medium">
diff --git a/packages/stage-ui/src/components/Providers/SpeechProviderSettings.vue b/packages/stage-ui/src/components/Providers/SpeechProviderSettings.vue
index 62114befd..5c452ccce 100644
--- a/packages/stage-ui/src/components/Providers/SpeechProviderSettings.vue
+++ b/packages/stage-ui/src/components/Providers/SpeechProviderSettings.vue
@@ -29,10 +29,7 @@ const props = defineProps<{
 // Expose slots and emit events to allow customization
 defineSlots<{
   'basic-settings': (props: any) => any
-  'voice-settings': (props: {
-    voiceSettings: Record<string, any>
-    updateVoiceSettings: (key: string, value: any) => void
-  }) => any
+  'voice-settings': (props: any) => any
   'advanced-settings': (props: any) => any
   'playground': (props: {
     isGenerating: boolean
diff --git a/packages/stage-ui/src/components/Providers/SpeechVoiceSettings.vue b/packages/stage-ui/src/components/Providers/SpeechVoiceSettings.vue
deleted file mode 100644
index 15d52e1ff..000000000
--- a/packages/stage-ui/src/components/Providers/SpeechVoiceSettings.vue
+++ /dev/null
@@ -1,102 +0,0 @@
-<script setup lang="ts">
-import { useI18n } from 'vue-i18n'
-
-import { FieldCheckbox, FieldRange } from '../index'
-
-defineProps<{
-  settings: Record<string, any>
-  // Which settings to show
-  showPitch?: boolean
-  showSpeed?: boolean
-  showStyle?: boolean
-  showStability?: boolean
-  showSimilarityBoost?: boolean
-  showVolume?: boolean
-  showSpeakerBoost?: boolean
-}>()
-
-const pitch = defineModel<number>('pitch', { required: false, default: 0 })
-const speed = defineModel<number>('speed', { required: false, default: 1.0 })
-const volume = defineModel<number>('volume', { required: false, default: 0 })
-const style = defineModel<number>('style', { required: false, default: 0 })
-const stability = defineModel<number>('stability', { required: false, default: 0.5 })
-const similarityBoost = defineModel<number>('similarityBoost', { required: false, default: 0.75 })
-const useSpeakerBoost = defineModel<boolean>('useSpeakerBoost', { required: false, default: false })
-
-const { t } = useI18n()
-</script>
-
-<template>
-  <div flex="~ col gap-4">
-    <!-- Pitch control - common to most providers -->
-    <FieldRange
-      v-if="showPitch"
-      v-model="pitch"
-      :label="t('settings.pages.providers.provider.common.fields.field.pitch.label')"
-      :description="t('settings.pages.providers.provider.common.fields.field.pitch.description')"
-      :min="-100"
-      :max="100" :step="1" :format-value="value => `${value}%`"
-    />
-
-    <!-- Speed control - common to most providers -->
-    <FieldRange
-      v-if="showSpeed"
-      v-model="speed"
-      :label="t('settings.pages.providers.provider.common.fields.field.speed.label')"
-      :description="t('settings.pages.providers.provider.common.fields.field.speed.description')"
-      :min="0.5"
-      :max="2.0" :step="0.01"
-    />
-
-    <!-- Volume control - available in some providers -->
-    <FieldRange
-      v-if="showVolume"
-      v-model="volume"
-      :label="t('settings.pages.providers.provider.common.fields.field.volume.label')"
-      :description="t('settings.pages.providers.provider.common.fields.field.volume.description')"
-      :min="-100"
-      :max="100" :step="1" :format-value="value => `${value}%`"
-    />
-
-    <!-- Style control - specific to ElevenLabs -->
-    <FieldRange
-      v-if="showStyle"
-      v-model="style"
-      :label="t('settings.pages.providers.provider.elevenlabs.fields.field.style.label')"
-      :description="t('settings.pages.providers.provider.elevenlabs.fields.field.style.description')"
-      :min="0"
-      :max="1" :step="0.01"
-    />
-
-    <!-- Stability control - specific to ElevenLabs -->
-    <FieldRange
-      v-if="showStability"
-      v-model="stability"
-      :label="t('settings.pages.providers.provider.elevenlabs.fields.field.stability.label')"
-      :description="t('settings.pages.providers.provider.elevenlabs.fields.field.stability.description')"
-      :min="0"
-      :max="1" :step="0.01"
-    />
-
-    <!-- Similarity Boost control - specific to ElevenLabs -->
-    <FieldRange
-      v-if="showSimilarityBoost"
-      v-model="similarityBoost"
-      :label="t('settings.pages.providers.provider.elevenlabs.fields.field.simularity-boost.label')"
-      :description="t('settings.pages.providers.provider.elevenlabs.fields.field.simularity-boost.description')"
-      :min="0"
-      :max="1" :step="0.01"
-    />
-
-    <!-- Speaker Boost checkbox - specific to ElevenLabs -->
-    <FieldCheckbox
-      v-if="showSpeakerBoost"
-      v-model="useSpeakerBoost"
-      :label="t('settings.pages.providers.provider.elevenlabs.fields.field.speaker-boost.label')"
-      :description="t('settings.pages.providers.provider.elevenlabs.fields.field.speaker-boost.description')"
-    />
-
-    <!-- Slot for additional provider-specific controls -->
-    <slot />
-  </div>
-</template>
diff --git a/packages/stage-ui/src/components/Providers/index.ts b/packages/stage-ui/src/components/Providers/index.ts
index 0e3d41681..81aa0337d 100644
--- a/packages/stage-ui/src/components/Providers/index.ts
+++ b/packages/stage-ui/src/components/Providers/index.ts
@@ -8,6 +8,4 @@ export { default as ProviderSettingsLayout2 } from './ProviderSettingsLayout2.vu
 export { default as ProviderSettingsLayout } from './ProviderSettingsLayout.vue'
 
 export { default as SpeechPlayground } from './SpeechPlayground.vue'
-// New speech provider components
 export { default as SpeechProviderSettings } from './SpeechProviderSettings.vue'
-export { default as SpeechVoiceSettings } from './SpeechVoiceSettings.vue'
diff --git a/packages/stage-ui/src/constants/elevenlabs.ts b/packages/stage-ui/src/constants/elevenlabs.ts
deleted file mode 100644
index 675e5ed87..000000000
--- a/packages/stage-ui/src/constants/elevenlabs.ts
+++ /dev/null
@@ -1,48 +0,0 @@
-export enum Voice {
-  // English
-  Myriam = 'Myriam',
-  Beatrice = 'Beatrice',
-  Camilla_KM = 'Camilla_KM',
-  SallySunshine = 'Sally Sunshine',
-  Annie = 'Annie',
-  KawaiiAerisita = 'Kawaii Aerisita',
-  // Japanese
-  Morioki = 'Morioki',
-}
-
-export const voiceMap: Record<Voice, string> = {
-  // English
-  [Voice.Myriam]: 'lNxY9WuCBCZCISASyJ55',
-  // Beatrice is not 'childish' like the others
-  // voice: 'Beatrice',
-  [Voice.Beatrice]: 'KAsXoQDshjF6ehsWa1mF',
-  [Voice.Camilla_KM]: 'dLhSyo03JRp5WkGpUlz1',
-  [Voice.SallySunshine]: 'qswttdunP3b44zVZKMRB',
-  [Voice.Annie]: 'AfA1PA0ldViH0DA6pbml',
-  [Voice.KawaiiAerisita]: 'vGQNBgLaiM3EdZtxIiuY',
-  // Japanese
-  [Voice.Morioki]: '8EkOjt4xTPGMclNlh1pk',
-}
-
-// voice: 'ShanShan',
-// Quite good for English
-
-export const enVoiceList = [
-  Voice.Myriam,
-  Voice.Beatrice,
-  Voice.Camilla_KM,
-  Voice.SallySunshine,
-  Voice.Annie,
-  Voice.KawaiiAerisita,
-]
-
-export const jaVoiceList = [
-  Voice.Morioki,
-]
-
-export const voiceList: Record<string, Voice[]> = {
-  'en': enVoiceList,
-  'en-US': enVoiceList,
-  'ja': jaVoiceList,
-  'ja-JP': jaVoiceList,
-}
diff --git a/packages/stage-ui/src/constants/index.ts b/packages/stage-ui/src/constants/index.ts
index 2f22705d0..cedbadabd 100644
--- a/packages/stage-ui/src/constants/index.ts
+++ b/packages/stage-ui/src/constants/index.ts
@@ -1,5 +1,4 @@
 export const llmInferenceEndToken = '<|llm_inference_end|>'
 
-export * from './elevenlabs'
 export * from './emotions'
 export * from './prompts/system-v2'
diff --git a/packages/stage-ui/src/stores/fix/elevenlabs.ts b/packages/stage-ui/src/stores/fix/elevenlabs.ts
deleted file mode 100644
index ab3d1729e..000000000
--- a/packages/stage-ui/src/stores/fix/elevenlabs.ts
+++ /dev/null
@@ -1,186 +0,0 @@
-import type { UnSpeechOptions } from '@xsai-ext/providers-local'
-import type { SpeechProviderWithExtraOptions } from '@xsai-ext/shared-providers'
-import type { VoiceProviderWithExtraOptions } from './voice'
-
-import { merge } from '@xsai-ext/shared-providers'
-import { objCamelToSnake } from '@xsai/shared'
-
-/** @see {@link https://elevenlabs.io/docs/api-reference/text-to-speech/convert#request} */
-export interface UnElevenLabsOptions {
-  /**
-   * This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto',
-   * the system will automatically decide whether to apply text normalization (e.g., spelling out numbers).
-   * With 'on', text normalization will always be applied, while with 'off', it will be skipped. Cannot be
-   * turned on for 'eleven_turbo_v2_5' model.
-   */
-  applyTextNormalization?: 'auto' | 'off' | 'on'
-  /**
-   * Language code (ISO 639-1) used to enforce a language for the model. Currently only Turbo v2.5
-   * supports language enforcement. For other models, an error will be returned if language code is provided.
-   */
-  languageCode?: string
-  /**
-   * A list of request_id of the samples that were generated before this generation. Can
-   * be used to improve the flow of prosody when splitting up a large task into multiple
-   * requests. The results will be best when the same model is used across the generations.
-   *
-   * In case both next_text and next_request_ids is send, next_text will be ignored.
-   * A maximum of 3 request_ids can be send.
-   */
-  nextRequestIds?: string[]
-  /**
-   * The text that comes after the text of the current request. Can be used to improve
-   * the flow of prosody when concatenating together multiple generations or to influence
-   * the prosody in the current generation.
-   */
-  nextText?: string
-  /**
-   * A list of request_id of the samples that were generated before this generation. Can be
-   * used to improve the flow of prosody when splitting up a large task into multiple requests.
-   * The results will be best when the same model is used across the generations. In case both
-   * previous_text and previous_request_ids is send, previous_text will be ignored. A maximum
-   * of 3 request_ids can be send.
-   */
-  previousRequestIds?: string[]
-  /**
-   * The text that came before the text of the current request. Can be used to improve the
-   * flow of prosody when concatenating together multiple generations or to influence the
-   * prosody in the current generation.
-   */
-  previousText?: string
-  /**
-   * A list of pronunciation dictionary locators (id, version_id) to be applied to the text.
-   * They will be applied in order. You may have up to 3 locators per request
-   */
-  pronunciationDictionaryLocators?: {
-    pronunciationDictionaryId: string
-    versionId: string
-  }[]
-  /**
-   * If specified, our system will make a best effort to sample deterministically, such that
-   * repeated requests with the same seed and parameters should return the same result.
-   * Determinism is not guaranteed. Must be integer between 0 and 4294967295.
-   */
-  seed?: number
-  /**
-   * Voice settings overriding stored settings for the given voice. They are applied only on the given request.
-   */
-  voiceSettings?: {
-    /**
-     * Determines how closely the AI should adhere to the original voice when attempting to replicate it.
-     */
-    similarityBoost: number
-    /**
-     * Controls the speed of the generated speech. Values range from 0.7 to 1.2, with 1.0 being the default
-     * speed. Lower values create slower, more deliberate speech while higher values produce faster-paced
-     * speech. Extreme values can impact the quality of the generated speech.
-     *
-     * @default 1.0
-     */
-    speed?: number
-    /**
-     * Determines how stable the voice is and the randomness between each generation. Lower values introduce
-     * broader emotional range for the voice. Higher values can result in a monotonous voice with limited
-     * emotion.
-     */
-    stability: number
-    /**
-     * Determines the style exaggeration of the voice. This setting attempts to amplify the style of the original
-     * speaker. It does consume additional computational resources and might increase latency if set to anything
-     * other than 0.
-     *
-     * @default 0
-     */
-    style?: number
-    /**
-     * This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher
-     * computational load, which in turn increases latency.
-     *
-     * @default true
-     */
-    useSpeakerBoost?: boolean
-  }
-}
-
-/**
- * [ElevenLabs](https://elevenlabs.io/) provider for [UnSpeech](https://github.com/moeru-ai/unspeech)
- * only.
- *
- * [UnSpeech](https://github.com/moeru-ai/unspeech) is a open-source project that provides a
- * OpenAI-compatible audio & speech related API that can be used with various providers such
- * as ElevenLabs, Azure TTS, Google TTS, etc.
- *
- * @param apiKey - ElevenLabs API Key
- * @param baseURL - UnSpeech Instance URL
- * @returns SpeechProviderWithExtraOptions
- */
-export function createUnElevenLabs(apiKey: string, baseURL = 'http://localhost:5933/v1/') {
-  const toUnSpeechOptions = ({
-    applyTextNormalization,
-    languageCode,
-    nextRequestIds,
-    nextText,
-    previousRequestIds,
-    previousText,
-    pronunciationDictionaryLocators,
-    seed,
-    voiceSettings,
-  }: UnElevenLabsOptions): UnSpeechOptions => ({
-    extraBody: objCamelToSnake({
-      applyTextNormalization,
-      languageCode,
-      nextRequestIds,
-      nextText,
-      previousRequestIds,
-      previousText,
-      pronunciationDictionaryLocators: pronunciationDictionaryLocators
-        ? pronunciationDictionaryLocators.map(pdl => objCamelToSnake(pdl))
-        : undefined,
-      seed,
-      voiceSettings: voiceSettings != null
-        ? objCamelToSnake(voiceSettings)
-        : {
-            similarityBoost: 0.75,
-            stability: 0.5,
-          },
-    }),
-  })
-
-  const speechProvider: SpeechProviderWithExtraOptions<
-    /** @see {@link https://elevenlabs.io/docs/developer-guides/models} */
-    'eleven_english_sts_v2' | 'eleven_flash_v2' | 'eleven_flash_v2_5' | 'eleven_multilingual_sts_v2' | 'eleven_multilingual_v2',
-    UnElevenLabsOptions
-  > = {
-    speech: (model, options) => ({
-      ...(options ? toUnSpeechOptions(options) : {}),
-      apiKey,
-      baseURL,
-      model: `elevenlabs/${model}`,
-    }),
-  }
-
-  const voiceProvider: VoiceProviderWithExtraOptions<
-    UnElevenLabsOptions
-  > = {
-    voice: (options) => {
-      if (baseURL.endsWith('v1/')) {
-        baseURL = baseURL.slice(0, -3)
-      }
-      else if (baseURL.endsWith('v1')) {
-        baseURL = baseURL.slice(0, -2)
-      }
-
-      return {
-        query: `provider=elevenlabs`,
-        ...(options ? toUnSpeechOptions(options) : {}),
-        apiKey,
-        baseURL,
-      }
-    },
-  }
-
-  return merge(
-    speechProvider,
-    voiceProvider,
-  )
-}
diff --git a/packages/stage-ui/src/stores/fix/list-voices.ts b/packages/stage-ui/src/stores/fix/list-voices.ts
deleted file mode 100644
index 65a13ffc4..000000000
--- a/packages/stage-ui/src/stores/fix/list-voices.ts
+++ /dev/null
@@ -1,22 +0,0 @@
-import type { CommonRequestOptions } from '@xsai/shared'
-import type { Voice } from './voice'
-
-import { requestHeaders, requestURL, responseJSON } from '@xsai/shared'
-
-export interface ListVoicesOptions extends Omit<CommonRequestOptions, 'model'> {
-  query?: string
-}
-
-export interface ListVoicesResponse {
-  voices: Voice[]
-}
-
-export async function listVoices(options: ListVoicesOptions): Promise<Voice[]> {
-  return (options.fetch ?? globalThis.fetch)(requestURL(options.query ? `api/voices?${options.query}` : 'api/voices', options.baseURL), {
-    headers: requestHeaders({ ...options.headers }, options.apiKey),
-    method: 'GET',
-    signal: options.abortSignal,
-  })
-    .then(responseJSON<ListVoicesResponse>)
-    .then(({ voices }) => voices)
-}
diff --git a/packages/stage-ui/src/stores/fix/microsoft.ts b/packages/stage-ui/src/stores/fix/microsoft.ts
deleted file mode 100644
index 4480a7fd4..000000000
--- a/packages/stage-ui/src/stores/fix/microsoft.ts
+++ /dev/null
@@ -1,174 +0,0 @@
-import type { UnSpeechOptions } from '@xsai-ext/providers-local'
-import type { SpeechProviderWithExtraOptions } from '@xsai-ext/shared-providers'
-import type { VoiceProviderWithExtraOptions } from './voice'
-
-import { merge } from '@xsai-ext/shared-providers'
-import { objCamelToSnake } from '@xsai/shared'
-
-export type MicrosoftRegions =
-  | 'australiaeast'
-  | 'brazilsouth'
-  | 'canadacentral'
-  | 'centralindia'
-  | 'centralus'
-  | 'eastasia'
-  | 'eastus2'
-  | 'eastus'
-  | 'francecentral'
-  | 'germanywestcentral'
-  | 'japaneast'
-  | 'japanwest'
-  | 'jioindiawest'
-  | 'koreacentral'
-  | 'northcentralus'
-  | 'northeurope'
-  | 'norwayeast'
-  | 'southcentralus'
-  | 'southeastasia'
-  | 'swedencentral'
-  | 'switzerlandnorth'
-  | 'switzerlandwest'
-  | 'uaenorth'
-  | 'uksouth'
-  | 'usgovarizona'
-  | 'usgovvirginia'
-  | 'westcentralus'
-  | 'westeurope'
-  | 'westus2'
-  | 'westus3'
-  | 'westus'
-
-export interface UnMicrosoftOptionAutoSSML {
-  gender:
-    | 'Female'
-    | 'Male'
-    | 'Neutral'
-    | string
-  lang:
-    | 'en-US'
-    | string
-  /**
-   * Speech Studio - Voice Gallery
-   * https://speech.microsoft.com/portal/018ba84135d64cf79106cc99c75ffa6a/voicegallery
-   */
-  voice:
-    | 'en-US-AndrewMultilingualNeural'
-    | 'en-US-AriaNeural'
-    | 'en-US-AvaMultilingualNeural'
-    | 'en-US-BrianMultilingualNeural'
-    | 'en-US-ChristopherMultilingualNeural'
-    | 'en-US-EmmaMultilingualNeural'
-    | 'en-US-JaneNeural'
-    | string
-}
-
-export interface UnMicrosoftOptionCommon {
-  /**
-   * Text to speech API reference (REST) - Speech service - Azure AI services | Microsoft Learn
-   * https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech?tabs=streaming#custom-neural-voices
-   */
-  deploymentId?: string
-  /**
-   * Text to speech API reference (REST) - Speech service - Azure AI services | Microsoft Learn
-   * https://learn.microsoft.com/en-us/azure/ai-services/speech-service/rest-text-to-speech?tabs=streaming#prebuilt-neural-voices
-   *
-   * NOTICE: Voices in preview are available in only these three regions: East US, West Europe, and Southeast Asia.
-   */
-  region: MicrosoftRegions | string
-  sampleRate?:
-    | 8000
-    | 16000
-    | 22050
-    | 24000
-    | 44100
-    | 48000
-    | number
-}
-
-export interface UnMicrosoftOptionCustomSSML {
-  /**
-   * By default, unspeech service will help you automatically convert OpenAI style plain text input
-   * into SSML with lang, gender, voice parameters, but if you ever wanted to provide your own SSML
-   * with all customizable parameters, you can set this option to `true` to disable the automatic
-   * conversion and use your own SSML instead.
-   *
-   * About SSML (Speech Synthesis Markup Language), @see {@link https://learn.microsoft.com/en-us/azure/ai-services/speech-service/speech-synthesis-markup}
-   */
-  disableSsml?: boolean
-}
-
-/** @see {@link https://elevenlabs.io/docs/api-reference/text-to-speech/convert#request} */
-export type UnMicrosoftOptions = (UnMicrosoftOptionAutoSSML | UnMicrosoftOptionCustomSSML) & UnMicrosoftOptionCommon
-
-/**
- * [Microsoft / Azure AI](https://speech.microsoft.com/portal) provider for [UnSpeech](https://github.com/moeru-ai/unspeech)
- * only.
- *
- * [UnSpeech](https://github.com/moeru-ai/unspeech) is a open-source project that provides a
- * OpenAI-compatible audio & speech related API that can be used with various providers such
- * as ElevenLabs, Azure TTS, Google TTS, etc.
- *
- * @param apiKey - Microsoft / Azure AI subscription key
- * @param baseURL - UnSpeech Instance URL
- * @returns SpeechProviderWithExtraOptions
- */
-export function createUnMicrosoft(apiKey: string, baseURL = 'http://localhost:5933/v1/') {
-  const toUnSpeechOptions = (options: UnMicrosoftOptions): UnSpeechOptions => {
-    const { deploymentId, region, sampleRate } = options
-
-    const extraBody: Record<string, unknown> = {
-      deploymentId,
-      region,
-      sampleRate,
-    }
-
-    if ('disableSsml' in options) {
-      extraBody.disableSsml = options.disableSsml
-    }
-    else if ('lang' in options) {
-      extraBody.lang = options.lang
-      extraBody.gender = options.gender
-      extraBody.voice = options.voice
-    }
-
-    return { extraBody: objCamelToSnake(extraBody) }
-  }
-
-  const speechProvider: SpeechProviderWithExtraOptions<
-    /** @see Currently, cognitive services are on v1 */
-    'microsoft/v1',
-    UnMicrosoftOptions
-  > = {
-    speech: (model, options) => ({
-      ...(options ? toUnSpeechOptions(options) : {}),
-      apiKey,
-      baseURL,
-      model: `microsoft/${model}`,
-    }),
-  }
-
-  const voiceProvider: VoiceProviderWithExtraOptions<
-    UnMicrosoftOptions
-  > = {
-    voice: (options) => {
-      if (baseURL.endsWith('v1/')) {
-        baseURL = baseURL.slice(0, -3)
-      }
-      else if (baseURL.endsWith('v1')) {
-        baseURL = baseURL.slice(0, -2)
-      }
-
-      return {
-        query: `region=${options?.region}&provider=microsoft`,
-        ...(options ? toUnSpeechOptions(options) : {}),
-        apiKey,
-        baseURL,
-      }
-    },
-  }
-
-  return merge(
-    speechProvider,
-    voiceProvider,
-  )
-}
diff --git a/packages/stage-ui/src/stores/fix/voice.ts b/packages/stage-ui/src/stores/fix/voice.ts
deleted file mode 100644
index 884be7971..000000000
--- a/packages/stage-ui/src/stores/fix/voice.ts
+++ /dev/null
@@ -1,41 +0,0 @@
-import type { CommonRequestOptions } from '@xsai/shared'
-
-export interface Voice {
-  compatible_models: string[]
-  description: string
-  formats: VoiceFormat[]
-  id: string
-  labels: Record<string, any> & {
-    accent?: string
-    age?: string
-    gender?: string
-    type?: string
-  }
-  languages: VoiceLanguage[]
-  name: string
-  predefined_options?: Record<string, any>
-  preview_audio_url?: string
-  tags: string[]
-}
-
-export interface VoiceFormat {
-  bitrate: number
-  extension: string
-  format_code: string
-  mime_type: string
-  name: string
-  sample_rate: number
-}
-
-export interface VoiceLanguage {
-  code: string
-  title: string
-}
-
-export interface VoiceProvider {
-  voice: () => Omit<CommonRequestOptions, 'model'> & { query?: string }
-}
-
-export interface VoiceProviderWithExtraOptions<T = undefined> {
-  voice: (options?: T) => Omit<CommonRequestOptions, 'model'> & { query?: string } & Partial<T>
-}
diff --git a/packages/stage-ui/src/stores/modules/speech.ts b/packages/stage-ui/src/stores/modules/speech.ts
index f054cdecf..90be93620 100644
--- a/packages/stage-ui/src/stores/modules/speech.ts
+++ b/packages/stage-ui/src/stores/modules/speech.ts
@@ -8,7 +8,6 @@ import { computed, onMounted, ref, watch } from 'vue'
 import { toXml } from 'xast-util-to-xml'
 import { x } from 'xastscript'
 
-import { voiceList, voiceMap } from '../../constants/elevenlabs'
 import { useProvidersStore } from '../providers'
 
 export const useSpeechStore = defineStore('speech', () => {
@@ -69,32 +68,12 @@ export const useSpeechStore = defineStore('speech', () => {
 
   const supportsSSML = computed(() => {
     // Currently only ElevenLabs and some other providers support SSML
-    return ['elevenlabs', 'microsoft-speech', 'azure-speech', 'google'].includes(activeSpeechProvider.value)
-  })
-
-  const availableLanguages = computed(() => {
-    return Object.keys(voiceList)
-  })
-
-  const availableVoicesForLanguage = computed(() => {
-    const language = selectedLanguage.value
-    if (!language || !voiceList[language]) {
-      return []
-    }
-
-    return voiceList[language].map(voiceEnum => ({
-      id: voiceMap[voiceEnum],
-      name: voiceEnum,
-      provider: 'elevenlabs',
-      language,
-    }))
+    return ['elevenlabs', 'microsoft-speech', 'azure-speech', 'google', 'alibaba-cloud-model-studio', 'volcengine'].includes(activeSpeechProvider.value)
   })
 
   // Helper function to determine if a provider is a speech provider
   function isSpeechProvider(providerId: string): boolean {
-    // This is a simplified check - in a real implementation, you might have a more robust way
-    // to determine if a provider supports speech synthesis
-    return ['elevenlabs', 'microsoft-speech', 'azure-speech', 'google', 'amazon'].includes(providerId)
+    return ['elevenlabs', 'microsoft-speech', 'azure-speech', 'google', 'amazon', 'alibaba-cloud-model-studio', 'volcengine'].includes(providerId)
   }
 
   async function loadVoicesForProvider(provider: string) {
@@ -247,8 +226,6 @@ export const useSpeechStore = defineStore('speech', () => {
     // Computed
     availableSpeechProvidersMetadata,
     supportsSSML,
-    availableLanguages,
-    availableVoicesForLanguage,
     supportsModelListing,
     providerModels,
     isLoadingActiveProviderModels,
diff --git a/packages/stage-ui/src/stores/providers.ts b/packages/stage-ui/src/stores/providers.ts
index 442e4080d..3f3e1c0ee 100644
--- a/packages/stage-ui/src/stores/providers.ts
+++ b/packages/stage-ui/src/stores/providers.ts
@@ -8,9 +8,13 @@ import type {
   TranscriptionProvider,
   TranscriptionProviderWithExtraOptions,
 } from '@xsai-ext/shared-providers'
-import type { UnElevenLabsOptions } from './fix/elevenlabs'
-import type { UnMicrosoftOptions } from './fix/microsoft'
-import type { VoiceProviderWithExtraOptions } from './fix/voice'
+import type {
+  UnAlibabaCloudOptions,
+  UnElevenLabsOptions,
+  UnMicrosoftOptions,
+  UnVolcengineOptions,
+  VoiceProviderWithExtraOptions,
+} from 'unspeech'
 
 import { useLocalStorage } from '@vueuse/core'
 import {
@@ -31,12 +35,16 @@ import {
 import { createOllama } from '@xsai-ext/providers-local'
 import { listModels } from '@xsai/model'
 import { defineStore } from 'pinia'
+import {
+  createUnAlibabaCloud,
+  createUnElevenLabs,
+  createUnMicrosoft,
+  createUnVolcengine,
+  listVoices,
+} from 'unspeech'
 import { computed, ref, watch } from 'vue'
 import { useI18n } from 'vue-i18n'
 
-import { createUnElevenLabs } from './fix/elevenlabs'
-import { listVoices } from './fix/list-voices'
-import { createUnMicrosoft } from './fix/microsoft'
 import { models as elevenLabsModels } from './providers/elevenlabs/list-models'
 
 export interface ProviderMetadata {
@@ -559,6 +567,112 @@ export const useProvidersStore = defineStore('providers', () => {
         },
       },
     },
+    'alibaba-cloud-model-studio': {
+      id: 'alibaba-cloud-model-studio',
+      nameKey: 'settings.pages.providers.provider.alibaba-cloud-model-studio.title',
+      name: 'Alibaba Cloud Model Studio',
+      descriptionKey: 'settings.pages.providers.provider.alibaba-cloud-model-studio.description',
+      description: 'bailian.console.aliyun.com',
+      iconColor: 'i-lobe-icons:alibabacloud',
+      defaultOptions: {
+        baseUrl: 'https://unspeech.hyp3r.link/v1/',
+      },
+      createProvider: config => createUnAlibabaCloud((config.apiKey as string).trim(), (config.baseUrl as string).trim()),
+      capabilities: {
+        listVoices: async (config) => {
+          const provider = createUnAlibabaCloud((config.apiKey as string).trim(), (config.baseUrl as string).trim()) as VoiceProviderWithExtraOptions<UnAlibabaCloudOptions>
+
+          const voices = await listVoices({
+            ...provider.voice(),
+          })
+
+          return voices.map((voice) => {
+            return {
+              id: voice.id,
+              name: voice.name,
+              provider: 'alibaba-cloud-model-studio',
+              previewURL: voice.preview_audio_url,
+              languages: voice.languages,
+              gender: voice.labels?.gender,
+            }
+          })
+        },
+        listModels: async () => {
+          return [
+            {
+              id: 'cozyvoice-v1',
+              name: 'CozyVoice',
+              provider: 'alibaba-cloud-model-studio',
+              description: '',
+              contextLength: 0,
+              deprecated: false,
+            },
+            {
+              id: 'cozyvoice-v2',
+              name: 'CozyVoice (New)',
+              provider: 'alibaba-cloud-model-studio',
+              description: '',
+              contextLength: 0,
+              deprecated: false,
+            },
+          ]
+        },
+      },
+      validators: {
+        validateProviderConfig: (config) => {
+          return !!config.apiKey && !!config.baseUrl
+        },
+      },
+    },
+    'volcengine': {
+      id: 'volcengine',
+      nameKey: 'settings.pages.providers.provider.volcengine.title',
+      name: 'settings.pages.providers.provider.volcengine.title',
+      descriptionKey: 'settings.pages.providers.provider.volcengine.description',
+      description: 'volcengine.com',
+      iconColor: 'i-lobe-icons:volcengine',
+      defaultOptions: {
+        baseUrl: 'https://unspeech.hyp3r.link/v1/',
+      },
+      createProvider: config => createUnVolcengine((config.apiKey as string).trim(), (config.baseUrl as string).trim()),
+      capabilities: {
+        listVoices: async (config) => {
+          const provider = createUnVolcengine((config.apiKey as string).trim(), (config.baseUrl as string).trim()) as VoiceProviderWithExtraOptions<UnVolcengineOptions>
+
+          const voices = await listVoices({
+            ...provider.voice(),
+          })
+
+          return voices.map((voice) => {
+            return {
+              id: voice.id,
+              name: voice.name,
+              provider: 'volcano-engine',
+              previewURL: voice.preview_audio_url,
+              languages: voice.languages,
+              gender: voice.labels?.gender,
+            }
+          })
+        },
+        listModels: async () => {
+          return [
+            {
+              id: 'v1',
+              name: 'v1',
+              provider: 'volcano-engine',
+              description: '',
+              contextLength: 0,
+              deprecated: false,
+            },
+          ]
+        },
+      },
+      validators: {
+        validateProviderConfig: (config) => {
+          return !!config.apiKey && !!config.baseUrl && !!config.app && !!(config.app as any).appId
+        },
+      },
+    },
     'together-ai': {
       id: 'together-ai',
       nameKey: 'settings.pages.providers.provider.together.title',
diff --git a/packages/stage-ui/src/stores/settings.ts b/packages/stage-ui/src/stores/settings.ts
index 40c607864..a9db4f246 100644
--- a/packages/stage-ui/src/stores/settings.ts
+++ b/packages/stage-ui/src/stores/settings.ts
@@ -3,7 +3,7 @@ import { converter } from 'culori'
 import { defineStore } from 'pinia'
 import { computed, ref, watch } from 'vue'
 
-export const DEFAULT_THEME_COLORS_HUE = 178.17
+export const DEFAULT_THEME_COLORS_HUE = 220.44
 
 const convert = converter('oklch')
 const getHueFrom = (color?: string) => color ? convert(color)?.h : DEFAULT_THEME_COLORS_HUE
diff --git a/packages/stage-ui/stories/ThemeColorsHueControl.vue b/packages/stage-ui/stories/ThemeColorsHueControl.vue
index ccecac557..413c51602 100644
--- a/packages/stage-ui/stories/ThemeColorsHueControl.vue
+++ b/packages/stage-ui/stories/ThemeColorsHueControl.vue
@@ -1,7 +1,7 @@
 <script setup lang="ts">
 import { onMounted, ref, watch } from 'vue'
 
-const DEFAULT_THEME_COLORS_HUE = 178.17
+const DEFAULT_THEME_COLORS_HUE = 220.44
 
 const themeColorsHue = ref(DEFAULT_THEME_COLORS_HUE)
 
diff --git a/packages/stage-ui/stories/themes.css b/packages/stage-ui/stories/themes.css
index 20760141c..347677a47 100644
--- a/packages/stage-ui/stories/themes.css
+++ b/packages/stage-ui/stories/themes.css
@@ -11,7 +11,7 @@
   --airi-theme-primary-900: #8e0d3b;
   --airi-theme-primary-950: #50011b;
 
-  --theme-colors-hue: 354.31;
+  --theme-colors-hue: 220.44;
   --theme-colors-chroma: calc(0.18 + (cos(var(--theme-colors-hue) * 3.14159265 / 180) * 0.04));
   --theme-colors-chroma-50: calc(var(--theme-colors-chroma) * 0.3);
   --theme-colors-chroma-100: calc(var(--theme-colors-chroma) * 0.5);
diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml
index 864e6cea3..db86ef960 100644
--- a/pnpm-lock.yaml
+++ b/pnpm-lock.yaml
@@ -1084,6 +1084,9 @@ importers:
       unist-builder:
         specifier: ^4.0.0
         version: 4.0.0
+      unspeech:
+        specifier: ^0.1.7
+        version: 0.1.7
       xast-util-to-xml:
         specifier: ^4.0.0
         version: 4.0.0
@@ -11151,6 +11154,9 @@ packages:
   unrs-resolver@1.3.2:
     resolution: {integrity: sha512-ZKQBC351Ubw0PY8xWhneIfb6dygTQeUHtCcNGd0QB618zabD/WbFMYdRyJ7xeVT+6G82K5v/oyZO0QSHFtbIuw==}
 
+  unspeech@0.1.7:
+    resolution: {integrity: sha512-HQ49mqEfvkMIKsbYDfHXDxbpUuNnb+gJdLO6wjQ/iPP1VuUfXs5Ky20attrRr1Qp2S0FHWsuz7/nlv9CAHHuhg==}
+
   unstorage@1.15.0:
     resolution: {integrity: sha512-m40eHdGY/gA6xAPqo8eaxqXgBuzQTlAKfmB1iF7oCKXE1HfwHwzDJBywK+qQGn52dta+bPlZluPF7++yR3p/bg==}
     peerDependencies:
@@ -23885,6 +23891,11 @@ snapshots:
       '@unrs/resolver-binding-win32-ia32-msvc': 1.3.2
       '@unrs/resolver-binding-win32-x64-msvc': 1.3.2
 
+  unspeech@0.1.7:
+    dependencies:
+      '@xsai-ext/shared-providers': 0.2.0-beta.3
+      '@xsai/shared': 0.2.0-beta.3
+
   unstorage@1.15.0:
     dependencies:
       anymatch: 3.1.3