增加语音对话功能

addon/content/chatpapers.css

@@ -752,3 +752,215 @@
 .chatpapers-cite-btn {
   flex-shrink: 0;
 }
+
+/* --- Voice lecture pane --- */
+.chatpapers-lecture-root {
+  gap: 10px;
+}
+
+.chatpapers-lecture-empty {
+  padding: 20px 12px;
+}
+
+.chatpapers-lecture-status {
+  padding: 8px 10px;
+  border-radius: 8px;
+  font-size: 12px;
+  line-height: 1.45;
+  background: color-mix(in srgb, #1f7a8c 10%, transparent);
+  border: 1px solid color-mix(in srgb, #1f7a8c 22%, transparent);
+}
+
+.chatpapers-lecture-status[data-status="failed"] {
+  background: color-mix(in srgb, #dc2626 10%, transparent);
+  border-color: color-mix(in srgb, #dc2626 25%, transparent);
+}
+
+.chatpapers-lecture-status[data-status="ready"] {
+  background: color-mix(in srgb, #16a34a 10%, transparent);
+  border-color: color-mix(in srgb, #16a34a 25%, transparent);
+}
+
+.chatpapers-lecture-actions {
+  display: flex;
+  gap: 8px;
+}
+
+.chatpapers-lecture-primary {
+  display: inline-flex;
+  align-items: center;
+  gap: 6px;
+  padding: 8px 14px;
+  border: none;
+  border-radius: 8px;
+  background: #1f7a8c;
+  color: #fff;
+  font-size: 13px;
+  font-weight: 600;
+  cursor: pointer;
+}
+
+.chatpapers-lecture-primary:hover:not(:disabled) {
+  background: #186678;
+}
+
+.chatpapers-lecture-status-text {
+  white-space: pre-line;
+}
+
+.chatpapers-lecture-primary:disabled {
+  opacity: 0.55;
+  cursor: not-allowed;
+}
+
+.chatpapers-lecture-secondary {
+  display: inline-flex;
+  align-items: center;
+  gap: 6px;
+  padding: 8px 14px;
+  border: 1px solid color-mix(in srgb, #1f7a8c 35%, transparent);
+  border-radius: 8px;
+  background: transparent;
+  color: inherit;
+  font-size: 13px;
+  font-weight: 600;
+  cursor: pointer;
+}
+
+.chatpapers-lecture-secondary:hover:not(:disabled) {
+  background: color-mix(in srgb, #1f7a8c 10%, transparent);
+}
+
+.chatpapers-lecture-secondary:disabled {
+  opacity: 0.55;
+  cursor: not-allowed;
+}
+
+.chatpapers-lecture-tts-meta {
+  font-size: 12px;
+  opacity: 0.75;
+}
+
+.chatpapers-lecture-audio {
+  width: 100%;
+  margin-top: 4px;
+}
+
+.chatpapers-lecture-btn-icon {
+  flex-shrink: 0;
+}
+
+.chatpapers-lecture-hint {
+  font-size: 11px;
+  opacity: 0.65;
+  line-height: 1.4;
+}
+
+.chatpapers-lecture-player {
+  display: flex;
+  flex-direction: column;
+  gap: 8px;
+  margin-top: 4px;
+}
+
+.chatpapers-lecture-player-title {
+  font-size: 12px;
+  font-weight: 600;
+  opacity: 0.85;
+}
+
+.chatpapers-lecture-beat-list {
+  display: flex;
+  flex-direction: column;
+  gap: 4px;
+  max-height: 220px;
+  overflow-y: auto;
+}
+
+.chatpapers-lecture-beat-item {
+  display: flex;
+  align-items: center;
+  justify-content: space-between;
+  gap: 8px;
+  padding: 8px 10px;
+  border: 1px solid color-mix(in srgb, #1f7a8c 18%, transparent);
+  border-radius: 8px;
+  background: color-mix(in srgb, #1f7a8c 4%, transparent);
+  cursor: pointer;
+  text-align: left;
+  font: inherit;
+  color: inherit;
+}
+
+.chatpapers-lecture-beat-item:hover:not(:disabled) {
+  background: color-mix(in srgb, #1f7a8c 10%, transparent);
+}
+
+.chatpapers-lecture-beat-item.is-active {
+  border-color: color-mix(in srgb, #16a34a 45%, transparent);
+  background: color-mix(in srgb, #16a34a 10%, transparent);
+}
+
+.chatpapers-lecture-beat-item.is-pending {
+  opacity: 0.55;
+  cursor: default;
+}
+
+.chatpapers-lecture-beat-meta {
+  display: flex;
+  flex-direction: column;
+  gap: 2px;
+  min-width: 0;
+}
+
+.chatpapers-lecture-beat-type {
+  font-size: 10px;
+  font-weight: 600;
+  opacity: 0.65;
+  text-transform: uppercase;
+  letter-spacing: 0.03em;
+}
+
+.chatpapers-lecture-beat-title {
+  font-size: 12px;
+  line-height: 1.35;
+  overflow: hidden;
+  text-overflow: ellipsis;
+  white-space: nowrap;
+}
+
+.chatpapers-lecture-beat-status {
+  flex-shrink: 0;
+  font-size: 11px;
+  opacity: 0.7;
+}
+
+.chatpapers-lecture-player-controls {
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  gap: 8px;
+}
+
+.chatpapers-lecture-player-btn {
+  display: inline-flex;
+  align-items: center;
+  justify-content: center;
+  width: 36px;
+  height: 36px;
+  border: 1px solid color-mix(in srgb, #1f7a8c 30%, transparent);
+  border-radius: 999px;
+  background: transparent;
+  cursor: pointer;
+  color: inherit;
+}
+
+.chatpapers-lecture-player-btn:hover {
+  background: color-mix(in srgb, #1f7a8c 12%, transparent);
+}
+
+.chatpapers-lecture-error {
+  padding: 12px;
+  color: #dc2626;
+  font-size: 12px;
+}

addon/content/icons/lecture.svg

@@ -0,0 +1,28 @@
+<svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 20 20" fill="none">
+  <!-- ChatPapers voice lecture: paper + headphones -->
+  <path
+    fill="context-fill"
+    fill-opacity="0.92"
+    d="M3.2 2.8h7.4c.4 0 .7.15.95.4l2.05 2.1c.25.25.4.58.4.95V14.2c0 .9-.73 1.63-1.63 1.63H3.2c-.9 0-1.63-.73-1.63-1.63V4.43C1.57 3.53 2.3 2.8 3.2 2.8z"
+  />
+  <path
+    fill="context-fill"
+    fill-opacity="0.35"
+    d="M10.6 2.85v2.35c0 .45.37.82.82.82h2.35L10.6 2.85z"
+  />
+  <path
+    stroke="context-stroke"
+    stroke-opacity="0.55"
+    stroke-width="0.9"
+    stroke-linecap="round"
+    d="M4.35 7.1h5.1M4.35 9.15h4.2"
+  />
+  <path
+    fill="context-fill"
+    d="M12.1 8.35c1.45 0 2.65 1.15 2.65 2.55v2.1c0 .35-.28.62-.62.62h-.75v1.05c0 .55-.45 1-1 1h-.55c-.55 0-1-.45-1-1v-1.05h-.55c-.35 0-.62-.28-.62-.62v-2.1c0-1.4 1.2-2.55 2.65-2.55z"
+  />
+  <path
+    fill="context-fill"
+    d="M16.55 9.05c1.05 0 1.9.82 1.9 1.85v1.35c0 1-.85 1.85-1.9 1.85-.35 0-.62-.28-.62-.62v-3.8c0-.35.28-.62.62-.62z"
+  />
+</svg>

addon/content/preferences.xhtml

@@ -116,6 +116,69 @@
   </hbox>
 </groupbox>
 
+<groupbox>
+  <label><html:h2 data-l10n-id="prefs-section-lecture"></html:h2></label>
+  <html:p id="chatpapers-pref-tts-hint" class="chatpapers-pref-hint"></html:p>
+
+  <hbox align="center">
+    <html:label
+      for="chatpapers-pref-tts-provider"
+      data-l10n-id="prefs-tts-provider"
+    ></html:label>
+    <html:select id="chatpapers-pref-tts-provider" preference="ttsProvider">
+    </html:select>
+  </hbox>
+
+  <hbox align="center">
+    <html:label
+      for="chatpapers-pref-tts-voice"
+      data-l10n-id="prefs-tts-voice"
+    ></html:label>
+    <html:input
+      type="text"
+      id="chatpapers-pref-tts-voice"
+      preference="ttsVoice"
+    ></html:input>
+  </hbox>
+
+  <vbox id="chatpapers-pref-piper-box" hidden="true">
+    <hbox align="center">
+      <html:label
+        for="chatpapers-pref-piper-path"
+        data-l10n-id="prefs-piper-path"
+      ></html:label>
+      <html:input
+        type="text"
+        id="chatpapers-pref-piper-path"
+        preference="piperPath"
+      ></html:input>
+    </hbox>
+    <hbox align="center">
+      <html:label
+        for="chatpapers-pref-piper-model"
+        data-l10n-id="prefs-piper-model"
+      ></html:label>
+      <html:input
+        type="text"
+        id="chatpapers-pref-piper-model"
+        preference="piperModelPath"
+      ></html:input>
+    </hbox>
+  </vbox>
+
+  <hbox align="center">
+    <html:label
+      for="chatpapers-pref-mineru-path"
+      data-l10n-id="prefs-mineru-path"
+    ></html:label>
+    <html:input
+      type="text"
+      id="chatpapers-pref-mineru-path"
+      preference="mineruPath"
+    ></html:input>
+  </hbox>
+</groupbox>
+
 <groupbox>
   <label><html:h2 data-l10n-id="prefs-section-prompts"></html:h2></label>
   <html:label data-l10n-id="prefs-system-prompt"></html:label>

addon/locale/en-US/addon.ftl

@@ -58,3 +58,38 @@ cite-empty = No styles available
 cite-copied = Bibliography copied
 cite-exported = Bibliography exported
 cite-export-cancel = Export cancelled
+
+item-section-lecture-head = Voice lecture
+item-section-lecture-sidenav = Voice lecture
+
+lecture-loading = Loading voice lecture…
+lecture-mode-label = Voice lecture · Prepare then listen
+lecture-empty-title = AI lecture mode
+lecture-empty-desc = One-click prep: overview and paragraph-by-paragraph listening, with typed Q&A and spoken answers.
+lecture-start = Start preparation
+lecture-status-idle = Click Start preparation — AI reads the full paper first
+lecture-status-preparing = Preparing lecture…
+lecture-status-ready = Lecture ready ✓
+lecture-status-ready-phase1 = Preparation done (Phase 1: summary ready)
+lecture-status-ready-step1 = Ready: { $count } segments — tap a segment or press Play
+lecture-status-failed = Preparation incomplete
+lecture-beat-list-title = Overview lecture
+lecture-play-start = Play
+lecture-play-pause = Pause
+lecture-play-next = Next
+lecture-play-prev = Previous
+lecture-play-complete = Playback finished
+lecture-beat-tts-pending = Synthesizing
+lecture-beat-tts-failed = Failed
+lecture-reprepare = Re-prepare
+lecture-no-pdf = No PDF attachment on this item
+lecture-attach-error = Cannot read PDF attachment
+lecture-mount-error = Failed to load voice lecture pane
+lecture-platform-hint-mac = macOS: set MinerU path under Preferences → ChatPapers → Voice lecture, or leave empty to use mineru on PATH.
+lecture-platform-hint-win = Windows: set the full path to mineru.exe under Preferences → ChatPapers → Voice lecture.
+lecture-platform-hint-other = Configure MinerU path in Preferences to enable structured PDF parsing.
+
+lecture-tts-provider = TTS: { $provider }
+lecture-tts-test = Test voice
+lecture-tts-testing = Synthesizing test speech…
+lecture-tts-test-done = Speech ready — playing

addon/locale/en-US/preferences.ftl

@@ -27,3 +27,11 @@ prefs-hint-cloud = Cloud provider: paper text is sent to the selected API endpoi
 prefs-models-empty = No models returned.
 prefs-models-pick = Enter a model id from the list (showing up to 30):
 prefs-privacy = Privacy: ChatPapers only sends content when you click Send/Summarize, and only to the endpoint you configured. API keys are stored in local Zotero preferences.
+
+prefs-section-lecture = Voice lecture
+prefs-tts-provider = TTS engine
+prefs-tts-voice = Voice (optional)
+prefs-piper-path = Piper executable
+prefs-piper-model = Piper model path (.onnx)
+prefs-mineru-path = MinerU path
+prefs-tts-hint-empty = Choose a TTS engine. Local engines are fully offline — no API key needed.

addon/locale/zh-CN/addon.ftl

@@ -59,3 +59,37 @@ cite-copied = 参考文献已复制到剪贴板
 cite-exported = 参考文献已导出
 cite-export-cancel = 已取消导出
 
+item-section-lecture-head = 语音伴读
+item-section-lecture-sidenav = 语音伴读
+
+lecture-loading = 正在加载语音伴读…
+lecture-mode-label = 语音伴读 · 先备课再听
+lecture-empty-title = AI 老师式伴读
+lecture-empty-desc = 一键备课：整体讲解与逐段精读，随时文字提问并获得语音回答。
+lecture-start = 开始备课
+lecture-status-idle = 点击「开始备课」，AI 将先读完整篇论文
+lecture-status-preparing = 正在备课…
+lecture-status-ready = 老师已备课 ✓
+lecture-status-ready-phase1 = 备课完成（Phase 1：摘要已生成）
+lecture-status-ready-step1 = 备课完成：{ $count } 段讲解可播放，点击下方段落或播放按钮开始听课
+lecture-status-failed = 备课未完成，请重试或检查 LLM 设置
+lecture-beat-list-title = 整体讲解
+lecture-play-start = 播放
+lecture-play-pause = 暂停
+lecture-play-next = 下一段
+lecture-play-prev = 上一段
+lecture-play-complete = 本轮讲解播放完毕
+lecture-beat-tts-pending = 合成中
+lecture-beat-tts-failed = 失败
+lecture-reprepare = 重新备课
+lecture-no-pdf = 当前条目没有可用的 PDF 附件
+lecture-attach-error = 无法读取 PDF 附件
+lecture-mount-error = 语音伴读面板加载失败
+lecture-platform-hint-mac = macOS：MinerU 路径可在偏好设置 → ChatPapers → 语音伴读 中配置；留空则尝试 PATH 中的 mineru。
+lecture-platform-hint-win = Windows：请在偏好设置中填写 MinerU 可执行文件完整路径（如 mineru.exe）。
+lecture-platform-hint-other = 请在偏好设置中配置 MinerU 路径以启用 PDF 结构化解析。
+
+lecture-tts-provider = TTS 引擎：{ $provider }
+lecture-tts-test = 试听语音
+lecture-tts-testing = 正在合成测试语音…
+lecture-tts-test-done = 语音合成完成，正在播放

addon/locale/zh-CN/preferences.ftl

@@ -27,3 +27,11 @@ prefs-hint-cloud = 云端 Provider：论文内容将发送到所选 API 端点
 prefs-models-empty = 未返回任何模型。
 prefs-models-pick = 从列表中输入模型 ID（最多显示 30 个）：
 prefs-privacy = 隐私说明：仅在你点击发送/总结时，向你配置的端点发送内容。API Key 仅保存在本地 Zotero 偏好设置中。
+
+prefs-section-lecture = 语音伴读
+prefs-tts-provider = TTS 引擎
+prefs-tts-voice = 音色（可选）
+prefs-piper-path = Piper 可执行文件
+prefs-piper-model = Piper 模型路径 (.onnx)
+prefs-mineru-path = MinerU 路径
+prefs-tts-hint-empty = 请选择 TTS 引擎。本地引擎完全离线，无需 API Key。

addon/manifest.json

@@ -14,7 +14,7 @@
       "id": "__addonID__",
       "update_url": "__updateURL__",
       "strict_min_version": "9.0",
-      "strict_max_version": "9.*"
+      "strict_max_version": "10.*"
     }
   }
 }

addon/prefs.js

@@ -13,3 +13,10 @@ pref("systemPrompt", "");
 pref("summaryPrompt", "");
 pref("sendMetadata", true);
 pref("verboseLog", false);
+pref("ttsProvider", "");
+pref("ttsApiKey", "");
+pref("ttsVoice", "");
+pref("lectureTeacherStyle", "balanced");
+pref("mineruPath", "");
+pref("piperPath", "");
+pref("piperModelPath", "");