feat: add asset library download button, fix env ports, update README, optimize semantics, support multi-image reading, and allow voiceover analysis for silent segments

lib/prompts/novel-promotion/voice_analysis.en.txt

@@ -34,5 +34,6 @@ Rules:
 4. Match panel by order + speaker consistency + semantic relevance.
 5. If no reliable panel match exists, set "matchedPanel": null.
 6. Use canonical names from character library when possible.
-7. Return strict JSON only, no markdown.
-8. ⚠️ JSON SAFETY: All quotation marks in dialogue (""''「」 etc.) MUST be converted to corner brackets「」in JSON string values. NEVER use raw ASCII double quotes " inside string values.
+7. If there is no spoken dialogue that should be voiced, return [].
+8. Return strict JSON only, no markdown.
+9. ⚠️ JSON SAFETY: All quotation marks in dialogue (""''「」 etc.) MUST be converted to corner brackets「」in JSON string values. NEVER use raw ASCII double quotes " inside string values.

lib/prompts/novel-promotion/voice_analysis.zh.txt

@@ -28,8 +28,10 @@
    - 动作描写（描述角色的动作）
    - 场景描述（描述环境、画面）
    - 章节标题
-   
+   - 明确设定为无语言、默片、纯画面表达的内容
+
    ⚠️ 判断标准：这句话是否需要有人"说出来"？如果只是描述画面动作，不要提取。
+   ⚠️ 如果全文没有任何需要配音的台词，直接返回 []。
 
 2. 【情绪强度 emotionStrength】
    根据台词的情绪激烈程度，输出0.1-0.5之间的数值（⚠️ 注意：最高不超过0.5，保持语音自然平稳）：