fix: strip dashes from TTS input (Kokoro was saying 'dash')

tests/test_voice.py

@@ -23,3 +23,10 @@ def test_speak_is_guarded_against_errors(monkeypatch):
     # even if a pipeline exists, a synth error must degrade to None, never raise
     monkeypatch.setattr(voice, "_PIPELINE", object())  # a bogus pipeline
     assert voice.speak("anything") is None
+
+
+def test_clean_for_tts_strips_dashes():
+    assert "—" not in voice._clean_for_tts("i don't— i don't remember")
+    assert "-" not in voice._clean_for_tts("a well-kept secret")
+    # collapses to single spaces, trims
+    assert voice._clean_for_tts("a  —  b") == "a , b"

voice.py

@@ -11,6 +11,7 @@ os.environ.setdefault("OPENBLAS_NUM_THREADS", "4")
 os.environ.setdefault("MKL_NUM_THREADS", "4")
 
 import base64
+import re
 
 import numpy as np
 
@@ -64,14 +65,24 @@ def _fog(x, intensity=_FILTER_INTENSITY, pitch=1.16):
     return (y / (np.max(np.abs(y)) + 1e-9) * 0.85).astype(np.float32)
 
 
+def _clean_for_tts(text: str) -> str:
+    """Kokoro verbalizes dashes ('—', '-') as words. Replace em/en dashes with a
+    comma pause and hyphens with a space, then collapse whitespace."""
+    text = text.replace("—", ", ").replace("–", ", ").replace("-", " ")
+    return re.sub(r"\s+", " ", text).strip()
+
+
 def speak(text: str) -> str | None:
     """Synthesize `text` as Hollow's whisper; return base64 WAV, or None if
     voice is unavailable or anything fails (never raises)."""
     if _PIPELINE is None or not text or not text.strip():
         return None
     try:
+        cleaned = _clean_for_tts(text)
+        if not cleaned:
+            return None
         audio = None
-        for _, _, chunk in _PIPELINE(text, voice=_VOICE, speed=_SPEED):
+        for _, _, chunk in _PIPELINE(cleaned, voice=_VOICE, speed=_SPEED):
             audio = chunk if audio is None else np.concatenate([audio, chunk])
         audio = np.asarray(audio, dtype=np.float32)
         audio = audio / (np.max(np.abs(audio)) + 1e-9) * 0.9