feat: integrate JV Voice Profile cloning, Voicebox research, and ensure session voice/markdown prompt nudge

spoken_text.py

@@ -30,6 +30,8 @@ _LIST_MARKER = re.compile(r"^[ \t]*[-*•]\s+", re.MULTILINE)
 _UNDERSCORE_WORD = re.compile(r"(?<=\w)_(?=\w)")
 _EXTRA_SPACE = re.compile(r"[ \t]{2,}")
 _CONTROL_TAGS = re.compile(r"\[(COMPLETE|NEEDS_DEEP|STATUS:[^\]]+)\]", re.IGNORECASE)
+_MARKDOWN_LINK = re.compile(r"\[([^\]]+)\]\((https?://[^\s)]+)\)")
+_BARE_URL = re.compile(r"https?://\S+")
 _VOICE_TAG = re.compile(r"\[Voice:\s*([a-zA-Z0-9_\-]+)\]", re.IGNORECASE)
 
 
@@ -56,6 +58,8 @@ class SpokenTextFilter(MarkdownTextFilter):
                     pass
 
         text = _TIMES.sub(" times ", text)
+        text = _MARKDOWN_LINK.sub(r"\1", text)
+        text = _BARE_URL.sub("", text)
         text = await super().filter(text)
         text = _CONTROL_TAGS.sub("", text)
         text = _STRIKETHROUGH.sub(r"\1", text)