Timmy_Foundation/hermes-agent
15
0
Fork 0
Code Issues 248 Pull Requests 14 Actions 1 Packages Projects Releases Wiki Activity

fix: add max recording timeout to prevent infinite wait in quiet environments

Browse Source 
AudioRecorder now auto-stops after 15 seconds if no speech is detected
(_has_spoken remains False). In quiet environments where ambient RMS
never exceeds the silence threshold (200), the recording would wait
indefinitely. The new _max_wait parameter fires the silence callback
after the timeout, triggering the normal "No speech detected" flow.
This commit is contained in:
0xbyt4
2026-03-10 17:41:56 +03:00
parent c3dc4448bf
commit 8b57a3cb7e
1 changed files with 23 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
tools/voice_mode.py
View File

@@ -185,6 +185,7 @@ class AudioRecorder:
self._on_silence_stop = None
self._silence_threshold: int = SILENCE_RMS_THRESHOLD
self._silence_duration: float = SILENCE_DURATION_SECONDS
self._max_wait: float = 15.0 # Max seconds to wait for speech before auto-stop
# Peak RMS seen during recording (for speech presence check in stop())
self._peak_rms: int = 0
# Live audio level (read by UI for visual feedback)
@@ -284,6 +285,10 @@ class AudioRecorder:
# else: brief dip, keep tolerating
# else: no speech attempt, just silence -- nothing to do
# Fire silence callback when:
# 1. User spoke then went silent for silence_duration, OR
# 2. No speech detected at all for max_wait seconds
should_fire = False
if self._has_spoken and rms <= self._silence_threshold:
# User was speaking and now is silent
if self._silence_start == 0.0:
@@ -291,15 +296,24 @@ class AudioRecorder:
elif now - self._silence_start >= self._silence_duration:
logger.info("Silence detected (%.1fs), auto-stopping",
self._silence_duration)
cb = self._on_silence_stop
self._on_silence_stop = None # fire only once
if cb:
def _safe_cb():
try:
cb()
except Exception as e:
logger.error("Silence callback failed: %s", e, exc_info=True)
threading.Thread(target=_safe_cb, daemon=True).start()
should_fire = True
elif not self._has_spoken and now - self._start_time >= self._max_wait:
# No speech detected within max_wait — stop to avoid
# infinite recording in quiet environments.
logger.info("No speech within %.0fs, auto-stopping",
self._max_wait)
should_fire = True
if should_fire:
cb = self._on_silence_stop
self._on_silence_stop = None # fire only once
if cb:
def _safe_cb():
try:
cb()
except Exception as e:
logger.error("Silence callback failed: %s", e, exc_info=True)
threading.Thread(target=_safe_cb, daemon=True).start()
try:
self._stream = sd.InputStream(