...

bolt_pet/audio/mic.py

@@ -44,6 +44,7 @@ def record_utterance(
     silence_end_sec: float = None,
     max_utterance_s: float = None,
     min_utterance_s: float = None,
+    grace_s: float = None,
     frame_len: int = config.FRAME_LEN,
     sample_rate: int = config.SAMPLE_RATE,
 ) -> Optional[np.ndarray]:
@@ -53,18 +54,24 @@ def record_utterance(
     *should_continue* is polled each frame so a caller can cancel recording
     (e.g. the pet window was closed) without needing threading primitives
     baked into this function.
+
+    *grace_s* is how long to wait for speech to *begin* before giving up.
+    The controller stretches it for follow-up questions, where you're being
+    asked something and need a moment to think rather than having just said
+    the wake word on purpose.
     """
     rms_threshold = config.RMS_THRESHOLD if rms_threshold is None else rms_threshold
     silence_end_sec = config.SILENCE_END_SEC if silence_end_sec is None else silence_end_sec
     max_utterance_s = config.MAX_UTTERANCE_S if max_utterance_s is None else max_utterance_s
     min_utterance_s = config.MIN_UTTERANCE_S if min_utterance_s is None else min_utterance_s
+    grace_s = config.GRACE_SECONDS if grace_s is None else grace_s
 
     frames: list[np.ndarray] = []
     started = False
     silence_frames = 0
     silence_limit = int(silence_end_sec * sample_rate / frame_len)
     max_frames = int(max_utterance_s * sample_rate / frame_len)
-    grace_frames = int(4.0 * sample_rate / frame_len)  # wait up to 4s for speech to begin
+    grace_frames = int(grace_s * sample_rate / frame_len)  # how long to wait for speech to begin
     waited = 0
 
     while should_continue():