abstractvoice 0.5.0__tar.gz → 0.5.2__tar.gz

{abstractvoice-0.5.0 → abstractvoice-0.5.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: abstractvoice
-Version: 0.5.0
+Version: 0.5.2
 Summary: A modular Python library for voice interactions with AI systems
 Author-email: Laurent-Philippe Albou <contact@abstractcore.ai>
 License-Expression: MIT
@@ -21,9 +21,9 @@ Requires-Dist: numpy>=1.24.0
 Requires-Dist: requests>=2.31.0
 Requires-Dist: appdirs>=1.4.0
 Requires-Dist: coqui-tts<0.30.0,>=0.27.0
-Requires-Dist: torch<2.4.0,>=2.0.0
-Requires-Dist: torchvision<0.19.0,>=0.15.0
-Requires-Dist: torchaudio<2.4.0,>=2.0.0
+Requires-Dist: torch<2.9.0,>=2.1.0
+Requires-Dist: torchvision<1.0.0,>=0.16.0
+Requires-Dist: torchaudio<2.9.0,>=2.1.0
 Requires-Dist: librosa>=0.10.0
 Requires-Dist: sounddevice>=0.4.6
 Requires-Dist: soundfile>=0.12.1
@@ -34,9 +34,9 @@ Requires-Dist: PyAudio>=0.2.13; extra == "voice"
 Requires-Dist: soundfile>=0.12.1; extra == "voice"
 Provides-Extra: tts
 Requires-Dist: coqui-tts<0.30.0,>=0.27.0; extra == "tts"
-Requires-Dist: torch<2.4.0,>=2.0.0; extra == "tts"
-Requires-Dist: torchvision<0.19.0,>=0.15.0; extra == "tts"
-Requires-Dist: torchaudio<2.4.0,>=2.0.0; extra == "tts"
+Requires-Dist: torch<2.9.0,>=2.1.0; extra == "tts"
+Requires-Dist: torchvision<1.0.0,>=0.16.0; extra == "tts"
+Requires-Dist: torchaudio<2.9.0,>=2.1.0; extra == "tts"
 Requires-Dist: librosa>=0.10.0; extra == "tts"
 Provides-Extra: stt
 Requires-Dist: openai-whisper>=20230314; extra == "stt"
@@ -49,9 +49,9 @@ Requires-Dist: webrtcvad>=2.0.10; extra == "all"
 Requires-Dist: PyAudio>=0.2.13; extra == "all"
 Requires-Dist: openai-whisper>=20230314; extra == "all"
 Requires-Dist: coqui-tts<0.30.0,>=0.27.0; extra == "all"
-Requires-Dist: torch<2.4.0,>=2.0.0; extra == "all"
-Requires-Dist: torchvision<0.19.0,>=0.15.0; extra == "all"
-Requires-Dist: torchaudio<2.4.0,>=2.0.0; extra == "all"
+Requires-Dist: torch<2.9.0,>=2.1.0; extra == "all"
+Requires-Dist: torchvision<1.0.0,>=0.16.0; extra == "all"
+Requires-Dist: torchaudio<2.9.0,>=2.1.0; extra == "all"
 Requires-Dist: librosa>=0.10.0; extra == "all"
 Requires-Dist: soundfile>=0.12.1; extra == "all"
 Requires-Dist: flask>=2.0.0; extra == "all"
@@ -66,17 +66,17 @@ Requires-Dist: webrtcvad>=2.0.10; extra == "voice-full"
 Requires-Dist: PyAudio>=0.2.13; extra == "voice-full"
 Requires-Dist: openai-whisper>=20230314; extra == "voice-full"
 Requires-Dist: coqui-tts<0.30.0,>=0.27.0; extra == "voice-full"
-Requires-Dist: torch<2.4.0,>=2.0.0; extra == "voice-full"
-Requires-Dist: torchvision<0.19.0,>=0.15.0; extra == "voice-full"
-Requires-Dist: torchaudio<2.4.0,>=2.0.0; extra == "voice-full"
+Requires-Dist: torch<2.9.0,>=2.1.0; extra == "voice-full"
+Requires-Dist: torchvision<1.0.0,>=0.16.0; extra == "voice-full"
+Requires-Dist: torchaudio<2.9.0,>=2.1.0; extra == "voice-full"
 Requires-Dist: librosa>=0.10.0; extra == "voice-full"
 Requires-Dist: soundfile>=0.12.1; extra == "voice-full"
 Requires-Dist: tiktoken>=0.6.0; extra == "voice-full"
 Provides-Extra: core-tts
 Requires-Dist: coqui-tts<0.30.0,>=0.27.0; extra == "core-tts"
-Requires-Dist: torch<2.4.0,>=2.0.0; extra == "core-tts"
-Requires-Dist: torchvision<0.19.0,>=0.15.0; extra == "core-tts"
-Requires-Dist: torchaudio<2.4.0,>=2.0.0; extra == "core-tts"
+Requires-Dist: torch<2.9.0,>=2.1.0; extra == "core-tts"
+Requires-Dist: torchvision<1.0.0,>=0.16.0; extra == "core-tts"
+Requires-Dist: torchaudio<2.9.0,>=2.1.0; extra == "core-tts"
 Requires-Dist: librosa>=0.10.0; extra == "core-tts"
 Provides-Extra: core-stt
 Requires-Dist: openai-whisper>=20230314; extra == "core-stt"
@@ -615,6 +615,37 @@ manager.set_tts_model("tts_models/en/ljspeech/glow-tts")
 # - "tts_models/en/ljspeech/glow-tts" (alternative fallback)
 # - "tts_models/en/ljspeech/tacotron2-DDC" (legacy)
 
+# === Audio Lifecycle Callbacks (v0.5.1+) ===
+
+# NEW: Precise audio timing callbacks for visual status indicators
+def on_synthesis_start():
+    print("🔴 Synthesis started - show thinking animation")
+
+def on_audio_start():
+    print("🔵 Audio started - show speaking animation")
+
+def on_audio_pause():
+    print("⏸️ Audio paused - show paused animation")
+
+def on_audio_resume():
+    print("▶️ Audio resumed - continue speaking animation")
+
+def on_audio_end():
+    print("🟢 Audio ended - show ready animation")
+
+def on_synthesis_end():
+    print("✅ Synthesis complete")
+
+# Wire up callbacks
+manager.tts_engine.on_playback_start = on_synthesis_start    # Existing (synthesis phase)
+manager.tts_engine.on_playback_end = on_synthesis_end        # Existing (synthesis phase)
+manager.on_audio_start = on_audio_start                      # NEW (actual audio playback)
+manager.on_audio_end = on_audio_end                          # NEW (actual audio playback)
+manager.on_audio_pause = on_audio_pause                      # NEW (pause events)
+manager.on_audio_resume = on_audio_resume                    # NEW (resume events)
+
+# Perfect for system tray icons, UI animations, or coordinating multiple audio streams
+
 # === STT (Speech-to-Text) ===
 
 def on_transcription(text):

{abstractvoice-0.5.0 → abstractvoice-0.5.2}/README.md

@@ -525,6 +525,37 @@ manager.set_tts_model("tts_models/en/ljspeech/glow-tts")
 # - "tts_models/en/ljspeech/glow-tts" (alternative fallback)
 # - "tts_models/en/ljspeech/tacotron2-DDC" (legacy)
 
+# === Audio Lifecycle Callbacks (v0.5.1+) ===
+
+# NEW: Precise audio timing callbacks for visual status indicators
+def on_synthesis_start():
+    print("🔴 Synthesis started - show thinking animation")
+
+def on_audio_start():
+    print("🔵 Audio started - show speaking animation")
+
+def on_audio_pause():
+    print("⏸️ Audio paused - show paused animation")
+
+def on_audio_resume():
+    print("▶️ Audio resumed - continue speaking animation")
+
+def on_audio_end():
+    print("🟢 Audio ended - show ready animation")
+
+def on_synthesis_end():
+    print("✅ Synthesis complete")
+
+# Wire up callbacks
+manager.tts_engine.on_playback_start = on_synthesis_start    # Existing (synthesis phase)
+manager.tts_engine.on_playback_end = on_synthesis_end        # Existing (synthesis phase)
+manager.on_audio_start = on_audio_start                      # NEW (actual audio playback)
+manager.on_audio_end = on_audio_end                          # NEW (actual audio playback)
+manager.on_audio_pause = on_audio_pause                      # NEW (pause events)
+manager.on_audio_resume = on_audio_resume                    # NEW (resume events)
+
+# Perfect for system tray icons, UI animations, or coordinating multiple audio streams
+
 # === STT (Speech-to-Text) ===
 
 def on_transcription(text):

{abstractvoice-0.5.0 → abstractvoice-0.5.2}/abstractvoice/__init__.py

@@ -32,5 +32,5 @@ from .voice_manager import VoiceManager
 # Import simple APIs for third-party applications
 from .simple_model_manager import list_models, download_model, get_status, is_ready
 
-__version__ = "0.5.0"
+__version__ = "0.5.2"
 __all__ = ['VoiceManager', 'list_models', 'download_model', 'get_status', 'is_ready'] 

{abstractvoice-0.5.0 → abstractvoice-0.5.2}/abstractvoice/tts/tts_engine.py

@@ -212,6 +212,13 @@ class NonBlockingAudioPlayer:
         self.current_position = 0
         self.playback_complete_callback = None
         
+        # NEW: Enhanced audio lifecycle callbacks
+        self.on_audio_start = None      # Called when first audio sample plays
+        self.on_audio_end = None        # Called when last audio sample finishes
+        self.on_audio_pause = None      # Called when audio is paused
+        self.on_audio_resume = None     # Called when audio is resumed
+        self._audio_started = False     # Track if we've fired start callback
+        
     def _audio_callback(self, outdata, frames, time, status):
         """Callback function for OutputStream - provides immediate pause/resume."""
         if status and self.debug_mode:
@@ -237,6 +244,12 @@ class NonBlockingAudioPlayer:
                     outdata.fill(0)
                     if self.is_playing:
                         self.is_playing = False
+                        self._audio_started = False  # Reset for next playback
+                        
+                        # Fire audio end callback
+                        if self.on_audio_end:
+                            threading.Thread(target=self.on_audio_end, daemon=True).start()
+                            
                         if self.playback_complete_callback:
                             # Call completion callback in a separate thread to avoid blocking
                             threading.Thread(target=self.playback_complete_callback, daemon=True).start()
@@ -246,6 +259,12 @@ class NonBlockingAudioPlayer:
             remaining = len(self.current_audio) - self.current_position
             frames_to_output = min(frames, remaining)
             
+            # Fire audio start callback on first real audio output
+            if frames_to_output > 0 and not self._audio_started:
+                self._audio_started = True
+                if self.on_audio_start:
+                    threading.Thread(target=self.on_audio_start, daemon=True).start()
+            
             # Output the audio data
             if frames_to_output > 0:
                 # Handle both mono and stereo output
@@ -344,6 +363,11 @@ class NonBlockingAudioPlayer:
                 self.is_paused = True
                 if self.debug_mode:
                     print(" > Audio paused immediately")
+                
+                # Fire audio pause callback
+                if self.on_audio_pause:
+                    threading.Thread(target=self.on_audio_pause, daemon=True).start()
+                
                 return True
         return False
     
@@ -354,6 +378,11 @@ class NonBlockingAudioPlayer:
                 self.is_paused = False
                 if self.debug_mode:
                     print(" > Audio resumed immediately")
+                
+                # Fire audio resume callback
+                if self.on_audio_resume:
+                    threading.Thread(target=self.on_audio_resume, daemon=True).start()
+                
                 return True
         return False
     
@@ -1264,4 +1293,5 @@ class TTSEngine:
         Returns:
             True if TTS is active, False otherwise
         """
-        return self.is_playing 
+        return self.is_playing
+    

{abstractvoice-0.5.0 → abstractvoice-0.5.2}/abstractvoice/voice_manager.py

@@ -241,6 +241,18 @@ class VoiceManager:
         self.tts_engine.on_playback_start = self._on_tts_start
         self.tts_engine.on_playback_end = self._on_tts_end
         
+        # NEW: Enhanced audio lifecycle callbacks (v0.5.1)
+        self.on_audio_start = None      # Called when first audio sample plays
+        self.on_audio_end = None        # Called when last audio sample finishes
+        self.on_audio_pause = None      # Called when audio is paused
+        self.on_audio_resume = None     # Called when audio is resumed
+        
+        # Wire callbacks directly to audio player (skip TTSEngine layer)
+        self.tts_engine.audio_player.on_audio_start = self._on_audio_start
+        self.tts_engine.audio_player.on_audio_end = self._on_audio_end
+        self.tts_engine.audio_player.on_audio_pause = self._on_audio_pause
+        self.tts_engine.audio_player.on_audio_resume = self._on_audio_resume
+        
         # Voice recognizer is initialized on demand
         self.voice_recognizer = None
         self.whisper_model = whisper_model
@@ -1030,4 +1042,24 @@ class VoiceManager:
             self.voice_recognizer.stop()
 
         self.stop_speaking()
-        return True 
+        return True
+    
+    def _on_audio_start(self):
+        """Called when audio actually starts playing."""
+        if self.on_audio_start:
+            self.on_audio_start()
+    
+    def _on_audio_end(self):
+        """Called when audio actually finishes playing."""
+        if self.on_audio_end:
+            self.on_audio_end()
+    
+    def _on_audio_pause(self):
+        """Called when audio is paused."""
+        if self.on_audio_pause:
+            self.on_audio_pause()
+    
+    def _on_audio_resume(self):
+        """Called when audio is resumed."""
+        if self.on_audio_resume:
+            self.on_audio_resume() 

{abstractvoice-0.5.0 → abstractvoice-0.5.2}/abstractvoice.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: abstractvoice
-Version: 0.5.0
+Version: 0.5.2
 Summary: A modular Python library for voice interactions with AI systems
 Author-email: Laurent-Philippe Albou <contact@abstractcore.ai>
 License-Expression: MIT
@@ -21,9 +21,9 @@ Requires-Dist: numpy>=1.24.0
 Requires-Dist: requests>=2.31.0
 Requires-Dist: appdirs>=1.4.0
 Requires-Dist: coqui-tts<0.30.0,>=0.27.0
-Requires-Dist: torch<2.4.0,>=2.0.0
-Requires-Dist: torchvision<0.19.0,>=0.15.0
-Requires-Dist: torchaudio<2.4.0,>=2.0.0
+Requires-Dist: torch<2.9.0,>=2.1.0
+Requires-Dist: torchvision<1.0.0,>=0.16.0
+Requires-Dist: torchaudio<2.9.0,>=2.1.0
 Requires-Dist: librosa>=0.10.0
 Requires-Dist: sounddevice>=0.4.6
 Requires-Dist: soundfile>=0.12.1
@@ -34,9 +34,9 @@ Requires-Dist: PyAudio>=0.2.13; extra == "voice"
 Requires-Dist: soundfile>=0.12.1; extra == "voice"
 Provides-Extra: tts
 Requires-Dist: coqui-tts<0.30.0,>=0.27.0; extra == "tts"
-Requires-Dist: torch<2.4.0,>=2.0.0; extra == "tts"
-Requires-Dist: torchvision<0.19.0,>=0.15.0; extra == "tts"
-Requires-Dist: torchaudio<2.4.0,>=2.0.0; extra == "tts"
+Requires-Dist: torch<2.9.0,>=2.1.0; extra == "tts"
+Requires-Dist: torchvision<1.0.0,>=0.16.0; extra == "tts"
+Requires-Dist: torchaudio<2.9.0,>=2.1.0; extra == "tts"
 Requires-Dist: librosa>=0.10.0; extra == "tts"
 Provides-Extra: stt
 Requires-Dist: openai-whisper>=20230314; extra == "stt"
@@ -49,9 +49,9 @@ Requires-Dist: webrtcvad>=2.0.10; extra == "all"
 Requires-Dist: PyAudio>=0.2.13; extra == "all"
 Requires-Dist: openai-whisper>=20230314; extra == "all"
 Requires-Dist: coqui-tts<0.30.0,>=0.27.0; extra == "all"
-Requires-Dist: torch<2.4.0,>=2.0.0; extra == "all"
-Requires-Dist: torchvision<0.19.0,>=0.15.0; extra == "all"
-Requires-Dist: torchaudio<2.4.0,>=2.0.0; extra == "all"
+Requires-Dist: torch<2.9.0,>=2.1.0; extra == "all"
+Requires-Dist: torchvision<1.0.0,>=0.16.0; extra == "all"
+Requires-Dist: torchaudio<2.9.0,>=2.1.0; extra == "all"
 Requires-Dist: librosa>=0.10.0; extra == "all"
 Requires-Dist: soundfile>=0.12.1; extra == "all"
 Requires-Dist: flask>=2.0.0; extra == "all"
@@ -66,17 +66,17 @@ Requires-Dist: webrtcvad>=2.0.10; extra == "voice-full"
 Requires-Dist: PyAudio>=0.2.13; extra == "voice-full"
 Requires-Dist: openai-whisper>=20230314; extra == "voice-full"
 Requires-Dist: coqui-tts<0.30.0,>=0.27.0; extra == "voice-full"
-Requires-Dist: torch<2.4.0,>=2.0.0; extra == "voice-full"
-Requires-Dist: torchvision<0.19.0,>=0.15.0; extra == "voice-full"
-Requires-Dist: torchaudio<2.4.0,>=2.0.0; extra == "voice-full"
+Requires-Dist: torch<2.9.0,>=2.1.0; extra == "voice-full"
+Requires-Dist: torchvision<1.0.0,>=0.16.0; extra == "voice-full"
+Requires-Dist: torchaudio<2.9.0,>=2.1.0; extra == "voice-full"
 Requires-Dist: librosa>=0.10.0; extra == "voice-full"
 Requires-Dist: soundfile>=0.12.1; extra == "voice-full"
 Requires-Dist: tiktoken>=0.6.0; extra == "voice-full"
 Provides-Extra: core-tts
 Requires-Dist: coqui-tts<0.30.0,>=0.27.0; extra == "core-tts"
-Requires-Dist: torch<2.4.0,>=2.0.0; extra == "core-tts"
-Requires-Dist: torchvision<0.19.0,>=0.15.0; extra == "core-tts"
-Requires-Dist: torchaudio<2.4.0,>=2.0.0; extra == "core-tts"
+Requires-Dist: torch<2.9.0,>=2.1.0; extra == "core-tts"
+Requires-Dist: torchvision<1.0.0,>=0.16.0; extra == "core-tts"
+Requires-Dist: torchaudio<2.9.0,>=2.1.0; extra == "core-tts"
 Requires-Dist: librosa>=0.10.0; extra == "core-tts"
 Provides-Extra: core-stt
 Requires-Dist: openai-whisper>=20230314; extra == "core-stt"
@@ -615,6 +615,37 @@ manager.set_tts_model("tts_models/en/ljspeech/glow-tts")
 # - "tts_models/en/ljspeech/glow-tts" (alternative fallback)
 # - "tts_models/en/ljspeech/tacotron2-DDC" (legacy)
 
+# === Audio Lifecycle Callbacks (v0.5.1+) ===
+
+# NEW: Precise audio timing callbacks for visual status indicators
+def on_synthesis_start():
+    print("🔴 Synthesis started - show thinking animation")
+
+def on_audio_start():
+    print("🔵 Audio started - show speaking animation")
+
+def on_audio_pause():
+    print("⏸️ Audio paused - show paused animation")
+
+def on_audio_resume():
+    print("▶️ Audio resumed - continue speaking animation")
+
+def on_audio_end():
+    print("🟢 Audio ended - show ready animation")
+
+def on_synthesis_end():
+    print("✅ Synthesis complete")
+
+# Wire up callbacks
+manager.tts_engine.on_playback_start = on_synthesis_start    # Existing (synthesis phase)
+manager.tts_engine.on_playback_end = on_synthesis_end        # Existing (synthesis phase)
+manager.on_audio_start = on_audio_start                      # NEW (actual audio playback)
+manager.on_audio_end = on_audio_end                          # NEW (actual audio playback)
+manager.on_audio_pause = on_audio_pause                      # NEW (pause events)
+manager.on_audio_resume = on_audio_resume                    # NEW (resume events)
+
+# Perfect for system tray icons, UI animations, or coordinating multiple audio streams
+
 # === STT (Speech-to-Text) ===
 
 def on_transcription(text):

{abstractvoice-0.5.0 → abstractvoice-0.5.2}/abstractvoice.egg-info/SOURCES.txt

@@ -23,4 +23,7 @@ abstractvoice/stt/transcriber.py
 abstractvoice/tts/__init__.py
 abstractvoice/tts/tts_engine.py
 abstractvoice/vad/__init__.py
-abstractvoice/vad/voice_detector.py
+abstractvoice/vad/voice_detector.py
+tests/test_callbacks.py
+tests/test_fresh_install.py
+tests/test_voice_switching.py

{abstractvoice-0.5.0 → abstractvoice-0.5.2}/abstractvoice.egg-info/requires.txt

@@ -2,9 +2,9 @@ numpy>=1.24.0
 requests>=2.31.0
 appdirs>=1.4.0
 coqui-tts<0.30.0,>=0.27.0
-torch<2.4.0,>=2.0.0
-torchvision<0.19.0,>=0.15.0
-torchaudio<2.4.0,>=2.0.0
+torch<2.9.0,>=2.1.0
+torchvision<1.0.0,>=0.16.0
+torchaudio<2.9.0,>=2.1.0
 librosa>=0.10.0
 sounddevice>=0.4.6
 soundfile>=0.12.1
@@ -15,9 +15,9 @@ webrtcvad>=2.0.10
 PyAudio>=0.2.13
 openai-whisper>=20230314
 coqui-tts<0.30.0,>=0.27.0
-torch<2.4.0,>=2.0.0
-torchvision<0.19.0,>=0.15.0
-torchaudio<2.4.0,>=2.0.0
+torch<2.9.0,>=2.1.0
+torchvision<1.0.0,>=0.16.0
+torchaudio<2.9.0,>=2.1.0
 librosa>=0.10.0
 soundfile>=0.12.1
 flask>=2.0.0
@@ -35,9 +35,9 @@ tiktoken>=0.6.0
 
 [core-tts]
 coqui-tts<0.30.0,>=0.27.0
-torch<2.4.0,>=2.0.0
-torchvision<0.19.0,>=0.15.0
-torchaudio<2.4.0,>=2.0.0
+torch<2.9.0,>=2.1.0
+torchvision<1.0.0,>=0.16.0
+torchaudio<2.9.0,>=2.1.0
 librosa>=0.10.0
 
 [dev]
@@ -51,9 +51,9 @@ tiktoken>=0.6.0
 
 [tts]
 coqui-tts<0.30.0,>=0.27.0
-torch<2.4.0,>=2.0.0
-torchvision<0.19.0,>=0.15.0
-torchaudio<2.4.0,>=2.0.0
+torch<2.9.0,>=2.1.0
+torchvision<1.0.0,>=0.16.0
+torchaudio<2.9.0,>=2.1.0
 librosa>=0.10.0
 
 [voice]
@@ -68,9 +68,9 @@ webrtcvad>=2.0.10
 PyAudio>=0.2.13
 openai-whisper>=20230314
 coqui-tts<0.30.0,>=0.27.0
-torch<2.4.0,>=2.0.0
-torchvision<0.19.0,>=0.15.0
-torchaudio<2.4.0,>=2.0.0
+torch<2.9.0,>=2.1.0
+torchvision<1.0.0,>=0.16.0
+torchaudio<2.9.0,>=2.1.0
 librosa>=0.10.0
 soundfile>=0.12.1
 tiktoken>=0.6.0

{abstractvoice-0.5.0 → abstractvoice-0.5.2}/pyproject.toml

@@ -29,9 +29,9 @@ dependencies = [
     "appdirs>=1.4.0",
     # Essential TTS dependencies for immediate functionality
     "coqui-tts>=0.27.0,<0.30.0",
-    "torch>=2.0.0,<2.4.0",
-    "torchvision>=0.15.0,<0.19.0",
-    "torchaudio>=2.0.0,<2.4.0",
+    "torch>=2.1.0,<2.9.0",
+    "torchvision>=0.16.0,<1.0.0",
+    "torchaudio>=2.1.0,<2.9.0",
     "librosa>=0.10.0",
     "sounddevice>=0.4.6",
     "soundfile>=0.12.1",
@@ -49,9 +49,9 @@ voice = [
 # Text-to-Speech functionality
 tts = [
     "coqui-tts>=0.27.0,<0.30.0",
-    "torch>=2.0.0,<2.4.0",
-    "torchvision>=0.15.0,<0.19.0",
-    "torchaudio>=2.0.0,<2.4.0",
+    "torch>=2.1.0,<2.9.0",
+    "torchvision>=0.16.0,<1.0.0",
+    "torchaudio>=2.1.0,<2.9.0",
     "librosa>=0.10.0",
 ]
 
@@ -73,9 +73,9 @@ all = [
     "PyAudio>=0.2.13",
     "openai-whisper>=20230314",
     "coqui-tts>=0.27.0,<0.30.0",
-    "torch>=2.0.0,<2.4.0",
-    "torchvision>=0.15.0,<0.19.0",
-    "torchaudio>=2.0.0,<2.4.0",
+    "torch>=2.1.0,<2.9.0",
+    "torchvision>=0.16.0,<1.0.0",
+    "torchaudio>=2.1.0,<2.9.0",
     "librosa>=0.10.0",
     "soundfile>=0.12.1",
     "flask>=2.0.0",
@@ -96,9 +96,9 @@ voice-full = [
     "PyAudio>=0.2.13",
     "openai-whisper>=20230314",
     "coqui-tts>=0.27.0,<0.30.0",
-    "torch>=2.0.0,<2.4.0",
-    "torchvision>=0.15.0,<0.19.0",
-    "torchaudio>=2.0.0,<2.4.0",
+    "torch>=2.1.0,<2.9.0",
+    "torchvision>=0.16.0,<1.0.0",
+    "torchaudio>=2.1.0,<2.9.0",
     "librosa>=0.10.0",
     "soundfile>=0.12.1",
     "tiktoken>=0.6.0",
@@ -107,9 +107,9 @@ voice-full = [
 # Core TTS-only (lightweight, no STT)
 core-tts = [
     "coqui-tts>=0.27.0,<0.30.0",
-    "torch>=2.0.0,<2.4.0",
-    "torchvision>=0.15.0,<0.19.0",
-    "torchaudio>=2.0.0,<2.4.0",
+    "torch>=2.1.0,<2.9.0",
+    "torchvision>=0.16.0,<1.0.0",
+    "torchaudio>=2.1.0,<2.9.0",
     "librosa>=0.10.0",
 ]
 

abstractvoice-0.5.2/tests/test_callbacks.py

@@ -0,0 +1,118 @@
+#!/usr/bin/env python3
+"""
+Test script for the new audio lifecycle callbacks in AbstractVoice v0.5.1
+
+This script demonstrates the precise timing of the new callback system.
+"""
+
+import time
+from abstractvoice import VoiceManager
+
+def test_audio_callbacks():
+    """Test the new audio lifecycle callbacks."""
+    
+    print("🧪 Testing AbstractVoice v0.5.1 Audio Lifecycle Callbacks")
+    print("=" * 60)
+    
+    # Callback tracking
+    events = []
+    
+    def on_synthesis_start():
+        events.append(("synthesis_start", time.time()))
+        print("🔴 Synthesis started - thinking phase")
+    
+    def on_audio_start():
+        events.append(("audio_start", time.time()))
+        print("🔵 Audio started - speaking phase")
+    
+    def on_audio_pause():
+        events.append(("audio_pause", time.time()))
+        print("⏸️ Audio paused")
+    
+    def on_audio_resume():
+        events.append(("audio_resume", time.time()))
+        print("▶️ Audio resumed")
+    
+    def on_audio_end():
+        events.append(("audio_end", time.time()))
+        print("🟢 Audio ended - ready phase")
+    
+    def on_synthesis_end():
+        events.append(("synthesis_end", time.time()))
+        print("✅ Synthesis complete")
+    
+    # Initialize VoiceManager
+    print("Initializing VoiceManager...")
+    vm = VoiceManager(debug_mode=True)
+    
+    # Wire up callbacks
+    vm.tts_engine.on_playback_start = on_synthesis_start
+    vm.tts_engine.on_playback_end = on_synthesis_end
+    vm.on_audio_start = on_audio_start
+    vm.on_audio_end = on_audio_end
+    vm.on_audio_pause = on_audio_pause
+    vm.on_audio_resume = on_audio_resume
+    
+    print("\n📢 Starting TTS with callback monitoring...")
+    
+    # Test basic playback
+    vm.speak("This is a test of the new audio lifecycle callbacks in AbstractVoice version zero point five point one.")
+    
+    # Wait a bit, then pause
+    time.sleep(2)
+    print("\n⏸️ Pausing audio...")
+    success = vm.pause_speaking()
+    if success:
+        print("✓ Pause successful")
+    
+    # Wait, then resume
+    time.sleep(2)
+    print("\n▶️ Resuming audio...")
+    success = vm.resume_speaking()
+    if success:
+        print("✓ Resume successful")
+    
+    # Wait for completion
+    while vm.is_speaking() or vm.is_paused():
+        time.sleep(0.1)
+    
+    # Analyze timing
+    print("\n📊 Callback Timing Analysis:")
+    print("-" * 40)
+    
+    if len(events) >= 2:
+        start_time = events[0][1]
+        for event_name, event_time in events:
+            offset = (event_time - start_time) * 1000  # Convert to milliseconds
+            print(f"{event_name:15} | +{offset:6.1f}ms")
+        
+        # Calculate key intervals
+        synthesis_to_audio = None
+        audio_duration = None
+        
+        for i, (event_name, event_time) in enumerate(events):
+            if event_name == "synthesis_start":
+                synthesis_start = event_time
+            elif event_name == "audio_start" and 'synthesis_start' in locals():
+                synthesis_to_audio = (event_time - synthesis_start) * 1000
+            elif event_name == "audio_end":
+                audio_end = event_time
+                # Find corresponding audio_start
+                for j in range(i-1, -1, -1):
+                    if events[j][0] == "audio_start":
+                        audio_duration = (audio_end - events[j][1]) * 1000
+                        break
+        
+        print("-" * 40)
+        if synthesis_to_audio:
+            print(f"Synthesis → Audio: {synthesis_to_audio:.1f}ms")
+        if audio_duration:
+            print(f"Audio Duration: {audio_duration:.1f}ms")
+    
+    # Cleanup
+    vm.cleanup()
+    print("\n✅ Test completed successfully!")
+    print("🎯 The new callbacks provide precise timing for visual status indicators.")
+
+if __name__ == "__main__":
+    test_callbacks()

abstractvoice-0.5.2/tests/test_fresh_install.py

@@ -0,0 +1,158 @@
+#!/usr/bin/env python3
+"""
+Test script that simulates fresh install behavior
+Tests language switching and voice selection with download requirements
+"""
+
+def test_language_switching():
+    """Test language switching with download behavior."""
+    from abstractvoice import VoiceManager
+
+    print("🧪 Testing Language Switching (Fresh Install Simulation)")
+    print("=" * 60)
+
+    vm = VoiceManager(debug_mode=True)
+
+    # Test languages
+    test_languages = [
+        ('fr', 'Bonjour, ceci est un test.', 'French'),
+        ('es', 'Hola, esta es una prueba.', 'Spanish'),
+        ('de', 'Hallo, das ist ein Test.', 'German'),
+        ('it', 'Ciao, questo è un test.', 'Italian'),
+        ('en', 'Back to English.', 'English'),
+    ]
+
+    for lang, text, name in test_languages:
+        print(f"\n🌍 Testing {name} ({lang})...")
+        success = vm.set_language(lang)
+
+        if success:
+            print(f"✅ {name}: Successfully loaded")
+            vm.speak(text, speed=1.0)
+        else:
+            print(f"❌ {name}: Failed to load")
+            print(f"   Run: abstractvoice download-models --language {lang}")
+
+    vm.cleanup()
+    print("\n✅ Language switching test complete!")
+
+
+def test_voice_switching():
+    """Test voice switching with download behavior."""
+    from abstractvoice import VoiceManager
+
+    print("\n🎭 Testing Voice Switching (Fresh Install Simulation)")
+    print("=" * 60)
+
+    vm = VoiceManager(debug_mode=True)
+
+    # Test different voices
+    test_voices = [
+        ('en', 'tacotron2', 'This is Linda voice.'),
+        ('en', 'jenny', 'This is Jenny voice.'),
+        ('en', 'ek1', 'This is Edward voice.'),
+        ('fr', 'css10_vits', 'Voix française.'),
+    ]
+
+    for lang, voice_id, text in test_voices:
+        print(f"\n🎤 Testing {lang}.{voice_id}...")
+        success = vm.set_voice(lang, voice_id)
+
+        if success:
+            print(f"✅ {voice_id}: Successfully loaded")
+            vm.speak(text)
+        else:
+            print(f"❌ {voice_id}: Failed to load")
+
+    vm.cleanup()
+    print("\n✅ Voice switching test complete!")
+
+
+def test_cli_commands():
+    """Test CLI commands for model management."""
+    from abstractvoice.examples.cli_repl import VoiceREPL
+
+    print("\n💻 Testing CLI Commands")
+    print("=" * 60)
+
+    cli = VoiceREPL()
+
+    # Test /language command
+    print("\n📝 Testing /language fr")
+    cli.onecmd('/language fr')
+
+    # Test /setvoice command
+    print("\n📝 Testing /setvoice en.jenny")
+    cli.onecmd('/setvoice en.jenny')
+
+    print("\n✅ CLI commands test complete!")
+
+
+def test_download_status():
+    """Test model download and status checking."""
+    from abstractvoice import is_ready, get_status
+    import json
+
+    print("\n📦 Testing Model Status")
+    print("=" * 60)
+
+    # Check if ready
+    ready = is_ready()
+    print(f"System ready: {ready}")
+
+    # Get detailed status
+    status = json.loads(get_status())
+    print(f"Total cached models: {status.get('total_cached', 0)}")
+    print(f"Cache size: {status.get('total_size_mb', 0):.1f} MB")
+    print(f"Ready for offline: {status.get('ready_for_offline', False)}")
+
+    # List cached models
+    if 'cached_models' in status:
+        print("\nCached models:")
+        for model in status['cached_models'][:5]:  # Show first 5
+            print(f"  • {model}")
+        if len(status['cached_models']) > 5:
+            print(f"  ... and {len(status['cached_models']) - 5} more")
+
+    print("\n✅ Model status test complete!")
+
+
+def main():
+    """Run all tests."""
+    import sys
+
+    print("🚀 AbstractVoice Fresh Install Simulation")
+    print("=" * 60)
+    print("This tests how the system behaves on a fresh install")
+    print("when models need to be downloaded.\n")
+
+    # Check command line arguments
+    if len(sys.argv) > 1:
+        if sys.argv[1] == '--language':
+            test_language_switching()
+        elif sys.argv[1] == '--voice':
+            test_voice_switching()
+        elif sys.argv[1] == '--cli':
+            test_cli_commands()
+        elif sys.argv[1] == '--status':
+            test_download_status()
+        else:
+            print("Usage: python test_fresh_install.py [--language|--voice|--cli|--status]")
+    else:
+        # Run all tests
+        test_download_status()
+        test_language_switching()
+        test_voice_switching()
+        test_cli_commands()
+
+        print("\n" + "=" * 60)
+        print("🎉 All fresh install tests complete!")
+        print("\nKey findings:")
+        print("  • Language switching downloads models if needed")
+        print("  • Voice switching downloads models if needed")
+        print("  • Clear error messages when downloads fail")
+        print("  • CLI commands properly handle missing models")
+
+
+if __name__ == "__main__":
+    main()

abstractvoice-0.5.2/tests/test_voice_switching.py

@@ -0,0 +1,87 @@
+#!/usr/bin/env python3
+"""
+Test script to verify voice switching works correctly.
+This will help us validate the fixes to the voice switching system.
+"""
+
+from abstractvoice import VoiceManager
+import time
+
+def test_voice_switching():
+    """Test voice switching to ensure different models actually load."""
+    print("🧪 Testing Voice Switching Fixes...")
+    print("=" * 50)
+
+    vm = VoiceManager(debug_mode=True)
+    print("✅ VoiceManager initialized")
+
+    # Test voices that should sound different
+    test_voices = [
+        ("en", "tacotron2"),  # Female LJSpeech
+        ("en", "jenny"),      # Different female
+        ("en", "ek1"),        # Male British
+    ]
+
+    print(f"\n🎭 Testing {len(test_voices)} different voices...")
+
+    for i, (lang, voice) in enumerate(test_voices):
+        print(f"\n--- Test {i+1}: {lang}.{voice} ---")
+
+        try:
+            # Set the voice and ensure it actually loads the requested model
+            success = vm.set_voice(lang, voice)
+
+            if success:
+                print(f"✅ Voice {voice} set successfully")
+
+                # Test speech with this voice
+                test_text = f"Hello, this is voice {voice}."
+                vm.speak(test_text, speed=1.0)
+
+                # Small delay between voice tests
+                time.sleep(1.0)
+
+            else:
+                print(f"❌ Failed to set voice {voice}")
+
+        except Exception as e:
+            print(f"💥 Exception with voice {voice}: {e}")
+
+    # Test language switching (should work without crashes)
+    print(f"\n🌍 Testing language switching...")
+
+    languages = ["en", "fr", "de"]
+    for lang in languages:
+        try:
+            success = vm.set_language(lang)
+            if success:
+                print(f"✅ Language {lang}: OK")
+                vm.speak(f"Testing {lang}", speed=1.0)
+                time.sleep(0.5)
+            else:
+                print(f"❌ Language {lang}: Failed")
+        except Exception as e:
+            print(f"💥 Language {lang}: Exception - {e}")
+
+    # Test Italian (the crash-prone one)
+    print(f"\n🇮🇹 Testing Italian models (crash safety)...")
+
+    italian_voices = ["mai_male_vits", "mai_female_vits"]
+    for voice in italian_voices:
+        try:
+            print(f"Testing it.{voice}...")
+            success = vm.set_voice("it", voice)
+            if success:
+                print(f"✅ Italian {voice}: Safe!")
+                vm.speak("Ciao, test italiano.", speed=0.8)  # Slower for Italian
+                time.sleep(0.5)
+            else:
+                print(f"⚠️ Italian {voice}: Skipped (safety)")
+        except Exception as e:
+            print(f"💥 Italian {voice}: Exception handled - {e}")
+
+    vm.cleanup()
+    print(f"\n🎉 Voice switching test complete!")
+
+if __name__ == "__main__":
+    test_voice_switching()