voice-mode 3.34.3__py3-none-any.whl → 4.0.1__py3-none-any.whl

voice_mode/frontend/package-lock.json

@@ -21,6 +21,7 @@
         "@types/node": "^20.17.13",
         "@types/react": "^18.3.18",
         "@types/react-dom": "^18.3.5",
+        "autoprefixer": "^10.4.21",
         "eslint": "^8.57.1",
         "eslint-config-next": "14.2.29",
         "eslint-config-prettier": "9.1.0",
@@ -1254,6 +1255,44 @@
         "node": ">= 0.4"
       }
     },
+    "node_modules/autoprefixer": {
+      "version": "10.4.21",
+      "resolved": "https://registry.npmjs.org/autoprefixer/-/autoprefixer-10.4.21.tgz",
+      "integrity": "sha512-O+A6LWV5LDHSJD3LjHYoNi4VLsj/Whi7k6zG12xTYaU4cQ8oxQGckXNX8cRHK5yOZ/ppVHe0ZBXGzSV9jXdVbQ==",
+      "dev": true,
+      "funding": [
+        {
+          "type": "opencollective",
+          "url": "https://opencollective.com/postcss/"
+        },
+        {
+          "type": "tidelift",
+          "url": "https://tidelift.com/funding/github/npm/autoprefixer"
+        },
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/ai"
+        }
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "browserslist": "^4.24.4",
+        "caniuse-lite": "^1.0.30001702",
+        "fraction.js": "^4.3.7",
+        "normalize-range": "^0.1.2",
+        "picocolors": "^1.1.1",
+        "postcss-value-parser": "^4.2.0"
+      },
+      "bin": {
+        "autoprefixer": "bin/autoprefixer"
+      },
+      "engines": {
+        "node": "^10 || ^12 || >=14"
+      },
+      "peerDependencies": {
+        "postcss": "^8.1.0"
+      }
+    },
     "node_modules/available-typed-arrays": {
       "version": "1.0.7",
       "dev": true,
@@ -1320,6 +1359,39 @@
         "node": ">=8"
       }
     },
+    "node_modules/browserslist": {
+      "version": "4.25.4",
+      "resolved": "https://registry.npmjs.org/browserslist/-/browserslist-4.25.4.tgz",
+      "integrity": "sha512-4jYpcjabC606xJ3kw2QwGEZKX0Aw7sgQdZCvIK9dhVSPh76BKo+C+btT1RRofH7B+8iNpEbgGNVWiLki5q93yg==",
+      "dev": true,
+      "funding": [
+        {
+          "type": "opencollective",
+          "url": "https://opencollective.com/browserslist"
+        },
+        {
+          "type": "tidelift",
+          "url": "https://tidelift.com/funding/github/npm/browserslist"
+        },
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/ai"
+        }
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "caniuse-lite": "^1.0.30001737",
+        "electron-to-chromium": "^1.5.211",
+        "node-releases": "^2.0.19",
+        "update-browserslist-db": "^1.1.3"
+      },
+      "bin": {
+        "browserslist": "cli.js"
+      },
+      "engines": {
+        "node": "^6 || ^7 || ^8 || ^9 || ^10 || ^11 || ^12 || >=13.7"
+      }
+    },
     "node_modules/busboy": {
       "version": "1.6.0",
       "dev": true,
@@ -1417,7 +1489,9 @@
       }
     },
     "node_modules/caniuse-lite": {
-      "version": "1.0.30001726",
+      "version": "1.0.30001739",
+      "resolved": "https://registry.npmjs.org/caniuse-lite/-/caniuse-lite-1.0.30001739.tgz",
+      "integrity": "sha512-y+j60d6ulelrNSwpPyrHdl+9mJnQzHBr08xm48Qno0nSk4h3Qojh+ziv2qE6rXf4k3tadF4o1J/1tAbVm1NtnA==",
       "dev": true,
       "funding": [
         {
@@ -1699,6 +1773,13 @@
       "dev": true,
       "license": "MIT"
     },
+    "node_modules/electron-to-chromium": {
+      "version": "1.5.211",
+      "resolved": "https://registry.npmjs.org/electron-to-chromium/-/electron-to-chromium-1.5.211.tgz",
+      "integrity": "sha512-IGBvimJkotaLzFnwIVgW9/UD/AOJ2tByUmeOrtqBfACSbAw5b1G0XpvdaieKyc7ULmbwXVx+4e4Be8pOPBrYkw==",
+      "dev": true,
+      "license": "ISC"
+    },
     "node_modules/emoji-regex": {
       "version": "9.2.2",
       "dev": true,
@@ -1865,6 +1946,16 @@
         "url": "https://github.com/sponsors/ljharb"
       }
     },
+    "node_modules/escalade": {
+      "version": "3.2.0",
+      "resolved": "https://registry.npmjs.org/escalade/-/escalade-3.2.0.tgz",
+      "integrity": "sha512-WUj2qlxaQtO4g6Pq5c29GTcWGDyd8itL8zTlipgECz3JesAiiOKotd8JU6otB3PACgG6xkJUyVhboMS+bje/jA==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=6"
+      }
+    },
     "node_modules/escape-string-regexp": {
       "version": "4.0.0",
       "dev": true,
@@ -2462,6 +2553,20 @@
         "url": "https://github.com/sponsors/isaacs"
       }
     },
+    "node_modules/fraction.js": {
+      "version": "4.3.7",
+      "resolved": "https://registry.npmjs.org/fraction.js/-/fraction.js-4.3.7.tgz",
+      "integrity": "sha512-ZsDfxO51wGAXREY55a7la9LScWpwv9RxIrYABrlvOFBlH/ShPnrtsXeuUIfXKKOVicNxQ+o8JTbJvjS4M89yew==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": "*"
+      },
+      "funding": {
+        "type": "patreon",
+        "url": "https://github.com/sponsors/rawify"
+      }
+    },
     "node_modules/framer-motion": {
       "version": "11.18.2",
       "resolved": "https://registry.npmjs.org/framer-motion/-/framer-motion-11.18.2.tgz",
@@ -3693,6 +3798,13 @@
         "node": "^10 || ^12 || >=14"
       }
     },
+    "node_modules/node-releases": {
+      "version": "2.0.19",
+      "resolved": "https://registry.npmjs.org/node-releases/-/node-releases-2.0.19.tgz",
+      "integrity": "sha512-xxOWJsBKtzAq7DY0J+DTzuz58K8e7sJbdgwkbMWQe8UYB6ekmsQ45q0M/tJDsGaZmbC+l7n57UV8Hl5tHxO9uw==",
+      "dev": true,
+      "license": "MIT"
+    },
     "node_modules/normalize-path": {
       "version": "3.0.0",
       "dev": true,
@@ -3701,6 +3813,16 @@
         "node": ">=0.10.0"
       }
     },
+    "node_modules/normalize-range": {
+      "version": "0.1.2",
+      "resolved": "https://registry.npmjs.org/normalize-range/-/normalize-range-0.1.2.tgz",
+      "integrity": "sha512-bdok/XvKII3nUpklnV6P2hxtMNrCboOjAcyBuQnWEhO665FwrSNRxU+AqpsyvO6LgGYPspN+lu5CLtw4jPRKNA==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=0.10.0"
+      }
+    },
     "node_modules/object-assign": {
       "version": "4.1.1",
       "dev": true,
@@ -5218,6 +5340,37 @@
         "@unrs/resolver-binding-win32-x64-msvc": "1.9.2"
       }
     },
+    "node_modules/update-browserslist-db": {
+      "version": "1.1.3",
+      "resolved": "https://registry.npmjs.org/update-browserslist-db/-/update-browserslist-db-1.1.3.tgz",
+      "integrity": "sha512-UxhIZQ+QInVdunkDAaiazvvT/+fXL5Osr0JZlJulepYu6Jd7qJtDZjlur0emRlT71EN3ScPoE7gvsuIKKNavKw==",
+      "dev": true,
+      "funding": [
+        {
+          "type": "opencollective",
+          "url": "https://opencollective.com/browserslist"
+        },
+        {
+          "type": "tidelift",
+          "url": "https://tidelift.com/funding/github/npm/browserslist"
+        },
+        {
+          "type": "github",
+          "url": "https://github.com/sponsors/ai"
+        }
+      ],
+      "license": "MIT",
+      "dependencies": {
+        "escalade": "^3.2.0",
+        "picocolors": "^1.1.1"
+      },
+      "bin": {
+        "update-browserslist-db": "cli.js"
+      },
+      "peerDependencies": {
+        "browserslist": ">= 4.21.0"
+      }
+    },
     "node_modules/uri-js": {
       "version": "4.4.1",
       "dev": true,

voice_mode/providers.py

@@ -9,9 +9,8 @@ import logging
 from typing import Dict, Optional, List, Any, Tuple
 from openai import AsyncOpenAI
 
-from .config import TTS_VOICES, TTS_MODELS, TTS_BASE_URLS, OPENAI_API_KEY
+from .config import TTS_VOICES, TTS_MODELS, TTS_BASE_URLS, OPENAI_API_KEY, get_voice_preferences
 from .provider_discovery import provider_registry, EndpointInfo
-from .voice_preferences import get_preferred_voices
 
 logger = logging.getLogger("voice-mode")
 
@@ -68,14 +67,14 @@ async def get_tts_client_and_voice(
         return client, selected_voice, selected_model, endpoint_info
     
     # Voice-first selection algorithm
-    # Get user preferences and prepend to system defaults
-    user_preferences = get_preferred_voices()
-    combined_voice_list = user_preferences + [v for v in TTS_VOICES if v not in user_preferences]
+    # Get user preferences from configuration
+    voice_preferences = get_voice_preferences()
+    combined_voice_list = voice_preferences
     
     logger.info(f"TTS Provider Selection (voice-first)")
-    if user_preferences:
-        logger.info(f"  User voice preferences: {user_preferences}")
-    logger.info(f"  Combined voice list: {combined_voice_list}")
+    if voice_preferences:
+        logger.info(f"  Voice preferences: {voice_preferences}")
+    logger.info(f"  Voice list: {combined_voice_list}")
     logger.info(f"  Preferred models: {TTS_MODELS}")
     logger.info(f"  Available endpoints: {TTS_BASE_URLS}")
     

voice_mode/resources/configuration.py

@@ -267,7 +267,7 @@ async def environment_variables() -> str:
         ("VOICEMODE_AUTO_START_KOKORO", "Auto-start Kokoro service (true/false)"),
         ("VOICEMODE_TTS_BASE_URLS", "Comma-separated list of TTS endpoints"),
         ("VOICEMODE_STT_BASE_URLS", "Comma-separated list of STT endpoints"),
-        ("VOICEMODE_TTS_VOICES", "Comma-separated list of preferred voices"),
+        ("VOICEMODE_VOICES", "Comma-separated list of preferred voices"),
         ("VOICEMODE_TTS_MODELS", "Comma-separated list of preferred models"),
         # Audio Settings
         ("VOICEMODE_AUDIO_FORMAT", "Audio format for recording (pcm/mp3/wav/flac/aac/opus)"),
@@ -358,7 +358,7 @@ async def environment_template() -> str:
         f"export VOICEMODE_AUTO_START_KOKORO=\"{str(AUTO_START_KOKORO).lower()}\"",
         f"export VOICEMODE_TTS_BASE_URLS=\"{','.join(TTS_BASE_URLS)}\"",
         f"export VOICEMODE_STT_BASE_URLS=\"{','.join(STT_BASE_URLS)}\"",
-        f"export VOICEMODE_TTS_VOICES=\"{','.join(TTS_VOICES)}\"",
+        f"export VOICEMODE_VOICES=\"{','.join(TTS_VOICES)}\"",
         f"export VOICEMODE_TTS_MODELS=\"{','.join(TTS_MODELS)}\"",
         "",
         "# Audio Settings",

voice_mode/tools/configuration_management.py

@@ -5,7 +5,7 @@ import re
 from pathlib import Path
 from typing import Dict, Optional, List
 from voice_mode.server import mcp
-from voice_mode.config import BASE_DIR
+from voice_mode.config import BASE_DIR, reload_configuration, find_voicemode_env_files
 import logging
 
 logger = logging.getLogger("voice-mode")
@@ -109,7 +109,7 @@ async def update_config(key: str, value: str) -> str:
     """Update a configuration value in the voicemode.env file.
     
     Args:
-        key: The configuration key to update (e.g., 'VOICEMODE_TTS_VOICES')
+        key: The configuration key to update (e.g., 'VOICEMODE_VOICES')
         value: The new value for the configuration
     
     Returns:
@@ -175,7 +175,7 @@ async def list_config_keys() -> str:
         ("Provider Configuration", [
             ("VOICEMODE_TTS_BASE_URLS", "Comma-separated list of TTS endpoints"),
             ("VOICEMODE_STT_BASE_URLS", "Comma-separated list of STT endpoints"),
-            ("VOICEMODE_TTS_VOICES", "Comma-separated list of preferred voices"),
+            ("VOICEMODE_VOICES", "Comma-separated list of preferred voices"),
             ("VOICEMODE_TTS_MODELS", "Comma-separated list of preferred models"),
             ("VOICEMODE_PREFER_LOCAL", "Prefer local providers over cloud (true/false)"),
             ("VOICEMODE_ALWAYS_TRY_LOCAL", "Always attempt local providers (true/false)"),
@@ -211,6 +211,107 @@ async def list_config_keys() -> str:
             lines.append(f"    {description}")
         lines.append("")
     
-    lines.append("💡 Usage: update_config(key='VOICEMODE_TTS_VOICES', value='af_sky,nova')")
+    lines.append("💡 Usage: update_config(key='VOICEMODE_VOICES', value='af_sky,nova')")
     
-    return "\n".join(lines)
+    return "\n".join(lines)
+
+
+@mcp.tool()
+async def config_reload() -> str:
+    """Reload configuration from .voicemode.env files and clear all caches.
+    
+    This tool reloads configuration from:
+    1. Global ~/.voicemode/voicemode.env file
+    2. Project-specific .voicemode.env files (searched up directory tree)
+    3. Environment variables (highest priority)
+    
+    Returns:
+        Status message showing which files were loaded and any changes
+    """
+    try:
+        # Get config files before reload
+        old_files = find_voicemode_env_files()
+        
+        # Reload configuration 
+        reload_configuration()
+        
+        # Get config files after reload
+        new_files = find_voicemode_env_files()
+        
+        lines = ["✅ Configuration reloaded successfully!", ""]
+        
+        if new_files:
+            lines.append("📁 Configuration files loaded (in order):")
+            for i, config_file in enumerate(new_files, 1):
+                lines.append(f"  {i}. {config_file}")
+        else:
+            lines.append("📁 No configuration files found - using defaults")
+        
+        lines.append("")
+        lines.append("🔄 All caches have been cleared")
+        lines.append("📊 Voice preferences and provider settings updated")
+        
+        logger.info(f"Configuration reloaded from {len(new_files)} files")
+        
+        return "\n".join(lines)
+        
+    except Exception as e:
+        logger.error(f"Failed to reload configuration: {e}")
+        return f"❌ Failed to reload configuration: {str(e)}"
+
+
+@mcp.tool()
+async def show_config_files() -> str:
+    """Show which .voicemode.env files are being used for configuration.
+    
+    This shows the current configuration file discovery and loading order:
+    - Global configuration from ~/.voicemode/voicemode.env
+    - Project-specific configuration (searched up directory tree)
+    - Current working directory for context
+    
+    Returns:
+        Formatted list of configuration files and their status
+    """
+    try:
+        config_files = find_voicemode_env_files()
+        
+        lines = ["📋 Voice Mode Configuration Files", "=" * 40, ""]
+        lines.append(f"🗂️  Current directory: {Path.cwd()}")
+        lines.append("")
+        
+        if config_files:
+            lines.append("📁 Configuration files (loading order):")
+            lines.append("")
+            
+            for i, config_file in enumerate(config_files, 1):
+                status = "✅ EXISTS" if config_file.exists() else "❌ MISSING"
+                file_type = ""
+                
+                if config_file.name == "voicemode.env" and config_file.parent.name == ".voicemode":
+                    if config_file.parent == Path.home() / ".voicemode":
+                        file_type = " (Global)"
+                    else:
+                        file_type = " (Project - in .voicemode dir)"
+                elif config_file.name == ".voicemode.env":
+                    if config_file.parent == Path.cwd():
+                        file_type = " (Project - current dir)"
+                    else:
+                        file_type = " (Project - parent dir)"
+                
+                lines.append(f"  {i}. {config_file}{file_type}")
+                lines.append(f"     {status}")
+                lines.append("")
+        else:
+            lines.append("❌ No configuration files found")
+            lines.append("")
+            lines.append("💡 Tip: Create ~/.voicemode/voicemode.env for global configuration")
+            lines.append("💡 Tip: Create .voicemode.env in project directories for project-specific settings")
+        
+        lines.append("")
+        lines.append("🔄 Use reload_config() to reload after making changes")
+        
+        return "\n".join(lines)
+        
+    except Exception as e:
+        logger.error(f"Failed to show config files: {e}")
+        return f"❌ Failed to show config files: {str(e)}"

voice_mode/tools/converse.py

@@ -875,6 +875,45 @@ def record_audio(duration: float) -> np.ndarray:
         logger.error(f"Recording failed: {e}")
         logger.error(f"Audio config when error occurred - Sample rate: {SAMPLE_RATE}, Channels: {CHANNELS}")
         
+        # Check if this is a device error that might be recoverable
+        error_str = str(e).lower()
+        if any(err in error_str for err in ['device unavailable', 'device disconnected', 
+                                             'invalid device', 'unanticipated host error',
+                                             'portaudio error']):
+            logger.info("Audio device error detected - attempting to reinitialize audio system")
+            
+            # Try to reinitialize sounddevice
+            try:
+                # Get current default device info before reinit
+                try:
+                    old_device = sd.query_devices(kind='input')
+                    old_device_name = old_device.get('name', 'Unknown')
+                except:
+                    old_device_name = 'Previous device'
+                
+                sd._terminate()
+                sd._initialize()
+                
+                # Get new default device info
+                try:
+                    new_device = sd.query_devices(kind='input')
+                    new_device_name = new_device.get('name', 'Unknown')
+                    logger.info(f"Audio system reinitialized - switched from '{old_device_name}' to '{new_device_name}'")
+                except:
+                    logger.info("Audio system reinitialized - retrying with new default device")
+                
+                # Wait a moment for the system to stabilize
+                import time as time_module
+                time_module.sleep(0.5)
+                
+                # Try recording again with the new device (recursive call)
+                logger.info("Retrying recording with new audio device...")
+                return record_audio(duration)
+                
+            except Exception as reinit_error:
+                logger.error(f"Failed to reinitialize audio: {reinit_error}")
+                # Fall through to normal error handling
+        
         # Import here to avoid circular imports
         from voice_mode.utils.audio_diagnostics import get_audio_error_help
         
@@ -989,6 +1028,14 @@ def record_audio_with_silence_detection(max_duration: float, disable_silence_det
             """Callback for continuous audio stream"""
             if status:
                 logger.warning(f"Audio stream status: {status}")
+                # Check for device-related errors
+                status_str = str(status).lower()
+                if any(err in status_str for err in ['device unavailable', 'device disconnected', 
+                                                      'invalid device', 'unanticipated host error',
+                                                      'stream is stopped', 'portaudio error']):
+                    # Signal that we should stop recording due to device error
+                    audio_queue.put(None)  # Sentinel value to indicate error
+                    return
             # Put the audio data in the queue for processing
             audio_queue.put(indata.copy())
         
@@ -1007,6 +1054,12 @@ def record_audio_with_silence_detection(max_duration: float, disable_silence_det
                         # Get audio chunk from queue with timeout
                         chunk = audio_queue.get(timeout=0.1)
                         
+                        # Check for error sentinel
+                        if chunk is None:
+                            logger.error("Audio device error detected - stopping recording")
+                            # Raise an exception to trigger recovery logic
+                            raise sd.PortAudioError("Audio device disconnected or unavailable")
+                        
                         # Flatten for consistency
                         chunk_flat = chunk.flatten()
                         chunks.append(chunk_flat)
@@ -1109,6 +1162,45 @@ def record_audio_with_silence_detection(max_duration: float, disable_silence_det
             # Import here to avoid circular imports
             from voice_mode.utils.audio_diagnostics import get_audio_error_help
             
+            # Check if this is a device error that might be recoverable
+            error_str = str(e).lower()
+            if any(err in error_str for err in ['device unavailable', 'device disconnected', 
+                                                 'invalid device', 'unanticipated host error',
+                                                 'portaudio error']):
+                logger.info("Audio device error detected - attempting to reinitialize audio system")
+                
+                # Try to reinitialize sounddevice
+                try:
+                    # Get current default device info before reinit
+                    try:
+                        old_device = sd.query_devices(kind='input')
+                        old_device_name = old_device.get('name', 'Unknown')
+                    except:
+                        old_device_name = 'Previous device'
+                    
+                    sd._terminate()
+                    sd._initialize()
+                    
+                    # Get new default device info
+                    try:
+                        new_device = sd.query_devices(kind='input')
+                        new_device_name = new_device.get('name', 'Unknown')
+                        logger.info(f"Audio system reinitialized - switched from '{old_device_name}' to '{new_device_name}'")
+                    except:
+                        logger.info("Audio system reinitialized - retrying with new default device")
+                    
+                    # Wait a moment for the system to stabilize
+                    import time as time_module
+                    time_module.sleep(0.5)
+                    
+                    # Try recording again with the new device (recursive call in sync context)
+                    logger.info("Retrying recording with new audio device...")
+                    return record_audio_with_silence_detection(max_duration, disable_silence_detection, min_duration, vad_aggressiveness)
+                    
+                except Exception as reinit_error:
+                    logger.error(f"Failed to reinitialize audio: {reinit_error}")
+                    # Fall through to normal error handling
+            
             # Get helpful error message
             help_message = get_audio_error_help(e)
             logger.error(f"\n{help_message}")
@@ -1555,6 +1647,12 @@ async def converse(
     # Run startup initialization if needed
     await startup_initialization()
     
+    # Refresh audio device cache to pick up any device changes (AirPods, etc.)
+    # This takes ~1ms and ensures we use the current default device
+    import sounddevice as sd
+    sd._terminate()
+    sd._initialize()
+    
     # Get event logger and start session
     event_logger = get_event_logger()
     session_id = None

voice_mode/tools/transcription/__init__.py

@@ -0,0 +1,14 @@
+"""Audio transcription with word-level timestamps."""
+
+from .types import TranscriptionBackend, OutputFormat, TranscriptionResult, WordData, SegmentData
+from .core import transcribe_audio, transcribe_audio_sync
+
+__all__ = [
+    'transcribe_audio',
+    'transcribe_audio_sync',
+    'TranscriptionBackend',
+    'OutputFormat',
+    'TranscriptionResult',
+    'WordData',
+    'SegmentData',
+]