修复网页对话并接入 SearXNG 搜索

app/voice/tts.py

@@ -45,6 +45,23 @@ _CLAUSE = "，,、：:"
 MAX_CHARS_PER_SEGMENT = 30
 
 
+def text_for_speech(text: str) -> str:
+    """去掉只适合屏幕阅读的链接/来源标记，避免 TTS 朗读网址。"""
+    text = text or ""
+    # 搜索回答约定把引用放在独立的“来源：”行；语音正文到此结束。
+    text = re.split(
+        r"(?:^|\n)\s*(?:参考来源|资料来源|来源)\s*[：:]",
+        text,
+        maxsplit=1,
+        flags=re.IGNORECASE,
+    )[0]
+    # 即使模型偶尔用了 Markdown 链接，也只朗读标题。
+    text = re.sub(r"\[([^\]]+)\]\(https?://[^)]+\)", r"\1", text)
+    text = re.sub(r"https?://\S+", "", text)
+    text = re.sub(r"[*#`|]", "", text)
+    return " ".join(text.split()).strip()
+
+
 class TTSError(RuntimeError):
     pass
 
@@ -154,4 +171,7 @@ class LocalTTS:
         return np.concatenate(chunks)
 
 
-__all__ = ["LocalTTS", "TTSError", "split_sentences", "MAX_CHARS_PER_SEGMENT"]
+__all__ = [
+    "LocalTTS", "TTSError", "split_sentences", "text_for_speech",
+    "MAX_CHARS_PER_SEGMENT",
+]