isu-admin/hearbit-ai-app
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 2 Wiki Activity

feat: improve meeting mode trigger to detect speech as fallback

Browse Source 
Meeting mode auto-start now triggers on system audio energy OR speech
detection (VAD). Fixes issue where Electron-based apps like Nextcloud
Talk were not triggering recording because ScreenCaptureKit didn't
capture their audio reliably. Also improved debug logging.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
michael.borak
2026-02-06 09:41:16 +01:00
parent 4803323087
commit 76ebe9e40c
1 changed files with 13 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
src-tauri/src/audio_processor.rs
View File

@@ -242,26 +242,33 @@ impl AudioProcessor {
// Threshold 0.01 is roughly -40dB, should cover ringtones/speech easily but ignore silence/hiss. // Threshold 0.01 is roughly -40dB, should cover ringtones/speech easily but ignore silence/hiss.
let system_active = max_system_energy > 0.005; let system_active = max_system_energy > 0.005;
// Periodically log energy to help debug why meeting mode might not start // Periodically log energy to help debug why meeting mode might not start
if self.last_event_time.elapsed().as_millis() > 2000 && self.recording_mode == "meeting" { if self.last_event_time.elapsed().as_millis() > 2000 && self.recording_mode == "meeting" {
if let Some(app) = &self.app_handle { if let Some(app) = &self.app_handle {
emit_log(app, "DEBUG", &format!("Waiting for Meeting... Current System Energy: {:.4} (Threshold: 0.005)", max_system_energy)); emit_log(app, "DEBUG", &format!(
"Waiting for Meeting... SysEnergy: {:.4} (thr: 0.005), VAD Speech: {} | SysQueue empty: {}",
max_system_energy, self.is_speech_active,
if let Ok(q) = self.system_queue.lock() { q.is_empty() } else { true }
));
} }
} }
// MODE-SPECIFIC TRIGGER LOGIC: // MODE-SPECIFIC TRIGGER LOGIC:
// "voice" -> Trigger if user speaks (is_speech_active) // "voice" -> Trigger if user speaks (VAD)
// "meeting" -> Trigger ONLY if system audio energy detected (Call starting) // "meeting" -> Trigger if system audio energy detected OR speech detected.
// Some apps (e.g. Electron-based Nextcloud Talk) may route audio
// in ways that ScreenCaptureKit doesn't always capture immediately.
// Allowing speech as a fallback trigger ensures calls are recorded.
let trigger = if self.recording_mode == "voice" { let trigger = if self.recording_mode == "voice" {
self.is_speech_active self.is_speech_active
} else { } else {
system_active system_active || self.is_speech_active
}; };
if trigger { if trigger {
// Trigger Detected! // Trigger Detected!
println!("Auto-Start: Call detected (SysEnergy: {}). Flushing pre-roll...", max_system_energy); println!("Auto-Start: Call detected (SysEnergy: {}, Speech: {}). Flushing pre-roll...", max_system_energy, self.is_speech_active);
self.waiting_for_speech = false; self.waiting_for_speech = false;
// Flush Ring Buffer (Orderly: from ring_pos to end, then 0 to ring_pos) // Flush Ring Buffer (Orderly: from ring_pos to end, then 0 to ring_pos)