voice-mode 2.33.0__py3-none-any.whl → 2.33.3__py3-none-any.whl

voice_mode/frontend/.next/types/app/api/connection-details/route.ts

@@ -1,4 +1,4 @@
-// File: /tmp/build-via-sdist-wr79qxwc/voice_mode-2.33.0/voice_mode/frontend/app/api/connection-details/route.ts
+// File: /tmp/build-via-sdist-i1skfj6s/voice_mode-2.33.3/voice_mode/frontend/app/api/connection-details/route.ts
 import * as entry from '../../../../../app/api/connection-details/route.js'
 import type { NextRequest } from 'next/server.js'
 

voice_mode/frontend/.next/types/app/layout.ts

@@ -1,4 +1,4 @@
-// File: /tmp/build-via-sdist-wr79qxwc/voice_mode-2.33.0/voice_mode/frontend/app/layout.tsx
+// File: /tmp/build-via-sdist-i1skfj6s/voice_mode-2.33.3/voice_mode/frontend/app/layout.tsx
 import * as entry from '../../../app/layout.js'
 import type { ResolvingMetadata, ResolvingViewport } from 'next/dist/lib/metadata/types/metadata-interface.js'
 

voice_mode/frontend/.next/types/app/page.ts

@@ -1,4 +1,4 @@
-// File: /tmp/build-via-sdist-wr79qxwc/voice_mode-2.33.0/voice_mode/frontend/app/page.tsx
+// File: /tmp/build-via-sdist-i1skfj6s/voice_mode-2.33.3/voice_mode/frontend/app/page.tsx
 import * as entry from '../../../app/page.js'
 import type { ResolvingMetadata, ResolvingViewport } from 'next/dist/lib/metadata/types/metadata-interface.js'
 

voice_mode/frontend/package-lock.json

@@ -1774,9 +1774,9 @@
       "license": "MIT"
     },
     "node_modules/electron-to-chromium": {
-      "version": "1.5.208",
-      "resolved": "https://registry.npmjs.org/electron-to-chromium/-/electron-to-chromium-1.5.208.tgz",
-      "integrity": "sha512-ozZyibehoe7tOhNaf16lKmljVf+3npZcJIEbJRVftVsmAg5TeA1mGS9dVCZzOwr2xT7xK15V0p7+GZqSPgkuPg==",
+      "version": "1.5.209",
+      "resolved": "https://registry.npmjs.org/electron-to-chromium/-/electron-to-chromium-1.5.209.tgz",
+      "integrity": "sha512-Xoz0uMrim9ZETCQt8UgM5FxQF9+imA7PBpokoGcZloA1uw2LeHzTlip5cb5KOAsXZLjh/moN2vReN3ZjJmjI9A==",
       "dev": true,
       "license": "ISC"
     },

voice_mode/templates/launchd/com.voicemode.whisper.plist

@@ -1,32 +1,26 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
-<!-- com.voicemode.whisper.plist v1.0.0 -->
-<!-- Last updated: 2025-01-25 -->
-<!-- Compatible with: whisper.cpp v1.5.0+ -->
+<!-- com.voicemode.whisper.plist v1.1.0 -->
+<!-- Last updated: 2025-08-25 -->
+<!-- Uses unified startup script for dynamic model selection -->
 <plist version="1.0">
 <dict>
     <key>Label</key>
     <string>com.voicemode.whisper</string>
     <key>ProgramArguments</key>
     <array>
-        <string>{WHISPER_BIN}</string>
-        <string>--host</string>
-        <string>0.0.0.0</string>
-        <string>--port</string>
-        <string>{WHISPER_PORT}</string>
-        <string>--model</string>
-        <string>{MODEL_FILE}</string>
+        <string>{START_SCRIPT_PATH}</string>
     </array>
     <key>RunAtLoad</key>
     <true/>
     <key>KeepAlive</key>
     <true/>
     <key>StandardOutPath</key>
-    <string>{LOG_DIR}/whisper.out.log</string>
+    <string>{LOG_DIR}/whisper/whisper.out.log</string>
     <key>StandardErrorPath</key>
-    <string>{LOG_DIR}/whisper.err.log</string>
+    <string>{LOG_DIR}/whisper/whisper.err.log</string>
     <key>WorkingDirectory</key>
-    <string>{WORKING_DIR}</string>
+    <string>{INSTALL_DIR}</string>
     <key>EnvironmentVariables</key>
     <dict>
         <key>PATH</key>

voice_mode/tools/services/whisper/install.py

@@ -219,7 +219,8 @@ async def whisper_install(
         if is_macos:
             # On macOS, always enable Metal
             cmake_flags.append("-DGGML_METAL=ON")
-            # On Apple Silicon, also enable Core ML for better performance
+            # On Apple Silicon, also enable Core ML support with fallback
+            # This allows using CoreML models if available, but falls back to Metal if not
             if platform.machine() == "arm64":
                 cmake_flags.append("-DWHISPER_COREML=ON")
                 cmake_flags.append("-DWHISPER_COREML_ALLOW_FALLBACK=ON")
@@ -318,7 +319,7 @@ async def whisper_install(
         template_content = None
         
         # First try to load from source if running in development
-        source_template = Path(__file__).parent.parent.parent.parent / "templates" / "scripts" / "start-whisper-server.sh"
+        source_template = Path(__file__).parent.parent.parent / "templates" / "scripts" / "start-whisper-server.sh"
         if source_template.exists():
             logger.info(f"Loading template from source: {source_template}")
             template_content = source_template.read_text()
@@ -331,90 +332,7 @@ async def whisper_install(
             except Exception as e:
                 logger.warning(f"Failed to load template script: {e}. Using fallback inline script.")
         
-        # Fallback to inline script if template not found
-        if template_content is None:
-            template_content = f"""#!/bin/bash
-
-# Whisper Service Startup Script
-# This script is used by both macOS (launchd) and Linux (systemd) to start the whisper service
-# It sources the voicemode.env file to get configuration, especially VOICEMODE_WHISPER_MODEL
-
-# Determine whisper directory (script is in bin/, whisper root is parent)
-SCRIPT_DIR="$(cd "$(dirname "${{BASH_SOURCE[0]}}")" && pwd)"
-WHISPER_DIR="$(dirname "$SCRIPT_DIR")"
-
-# Voicemode configuration directory
-VOICEMODE_DIR="$HOME/.voicemode"
-LOG_DIR="$VOICEMODE_DIR/logs/whisper"
-
-# Create log directory if it doesn't exist
-mkdir -p "$LOG_DIR"
-
-# Log file for this script (separate from whisper server logs)
-STARTUP_LOG="$LOG_DIR/startup.log"
-
-# Source voicemode configuration if it exists
-if [ -f "$VOICEMODE_DIR/voicemode.env" ]; then
-    echo "[$(date '+%Y-%m-%d %H:%M:%S')] Sourcing voicemode.env" >> "$STARTUP_LOG"
-    source "$VOICEMODE_DIR/voicemode.env"
-else
-    echo "[$(date '+%Y-%m-%d %H:%M:%S')] Warning: voicemode.env not found" >> "$STARTUP_LOG"
-fi
-
-# Model selection with environment variable support
-MODEL_NAME="${{VOICEMODE_WHISPER_MODEL:-base}}"
-MODEL_PATH="$WHISPER_DIR/models/ggml-$MODEL_NAME.bin"
-
-echo "[$(date '+%Y-%m-%d %H:%M:%S')] Starting whisper-server with model: $MODEL_NAME" >> "$STARTUP_LOG"
-
-# Check if model exists
-if [ ! -f "$MODEL_PATH" ]; then
-    echo "[$(date '+%Y-%m-%d %H:%M:%S')] Error: Model $MODEL_NAME not found at $MODEL_PATH" >> "$STARTUP_LOG"
-    echo "[$(date '+%Y-%m-%d %H:%M:%S')] Available models:" >> "$STARTUP_LOG"
-    ls -1 "$WHISPER_DIR/models/" 2>/dev/null | grep "^ggml-.*\\.bin$" >> "$STARTUP_LOG"
-    
-    # Try to find any available model as fallback
-    FALLBACK_MODEL=$(ls -1 "$WHISPER_DIR/models/" 2>/dev/null | grep "^ggml-.*\\.bin$" | head -1)
-    if [ -n "$FALLBACK_MODEL" ]; then
-        MODEL_PATH="$WHISPER_DIR/models/$FALLBACK_MODEL"
-        echo "[$(date '+%Y-%m-%d %H:%M:%S')] Using fallback model: $FALLBACK_MODEL" >> "$STARTUP_LOG"
-    else
-        echo "[$(date '+%Y-%m-%d %H:%M:%S')] Fatal: No whisper models found" >> "$STARTUP_LOG"
-        exit 1
-    fi
-fi
-
-# Port configuration (with environment variable support)
-WHISPER_PORT="${{VOICEMODE_WHISPER_PORT:-2022}}"
-
-# Determine server binary location
-# Check new CMake build location first, then legacy location
-if [ -f "$WHISPER_DIR/build/bin/whisper-server" ]; then
-    SERVER_BIN="$WHISPER_DIR/build/bin/whisper-server"
-elif [ -f "$WHISPER_DIR/server" ]; then
-    SERVER_BIN="$WHISPER_DIR/server"
-else
-    echo "[$(date '+%Y-%m-%d %H:%M:%S')] Error: whisper-server binary not found" >> "$STARTUP_LOG"
-    echo "[$(date '+%Y-%m-%d %H:%M:%S')] Checked: $WHISPER_DIR/build/bin/whisper-server" >> "$STARTUP_LOG"
-    echo "[$(date '+%Y-%m-%d %H:%M:%S')] Checked: $WHISPER_DIR/server" >> "$STARTUP_LOG"
-    exit 1
-fi
-
-echo "[$(date '+%Y-%m-%d %H:%M:%S')] Using binary: $SERVER_BIN" >> "$STARTUP_LOG"
-echo "[$(date '+%Y-%m-%d %H:%M:%S')] Model path: $MODEL_PATH" >> "$STARTUP_LOG"
-echo "[$(date '+%Y-%m-%d %H:%M:%S')] Port: $WHISPER_PORT" >> "$STARTUP_LOG"
-
-# Start whisper-server
-# Using exec to replace this script process with whisper-server
-cd "$WHISPER_DIR"
-exec "$SERVER_BIN" \\
-    --host 0.0.0.0 \\
-    --port "$WHISPER_PORT" \\
-    --model "$MODEL_PATH" \\
-    --inference-path /v1/audio/transcriptions \\
-    --threads 8
-"""
-        
+        # Create the start script (whether template was loaded from file or created inline)
         start_script_path = os.path.join(bin_dir, "start-whisper-server.sh")
         with open(start_script_path, 'w') as f:
             f.write(template_content)
@@ -433,33 +351,22 @@ exec "$SERVER_BIN" \\
             plist_name = "com.voicemode.whisper.plist"
             plist_path = os.path.join(launchagents_dir, plist_name)
             
-            plist_content = f"""<?xml version="1.0" encoding="UTF-8"?>
-<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
-<plist version="1.0">
-<dict>
-    <key>Label</key>
-    <string>com.voicemode.whisper</string>
-    <key>ProgramArguments</key>
-    <array>
-        <string>{start_script_path}</string>
-    </array>
-    <key>WorkingDirectory</key>
-    <string>{install_dir}</string>
-    <key>RunAtLoad</key>
-    <true/>
-    <key>KeepAlive</key>
-    <true/>
-    <key>StandardOutPath</key>
-    <string>{os.path.join(voicemode_dir, 'logs', 'whisper', 'whisper.out.log')}</string>
-    <key>StandardErrorPath</key>
-    <string>{os.path.join(voicemode_dir, 'logs', 'whisper', 'whisper.err.log')}</string>
-    <key>EnvironmentVariables</key>
-    <dict>
-        <key>PATH</key>
-        <string>/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin:/opt/homebrew/bin</string>
-    </dict>
-</dict>
-</plist>"""
+            # Load plist template
+            # First try to load from source if running in development
+            source_template = Path(__file__).parent.parent.parent / "templates" / "launchd" / "com.voicemode.whisper.plist"
+            if source_template.exists():
+                logger.info(f"Loading plist template from source: {source_template}")
+                plist_content = source_template.read_text()
+            else:
+                # Load from package resources
+                template_resource = files("voice_mode.templates.launchd").joinpath("com.voicemode.whisper.plist")
+                plist_content = template_resource.read_text()
+                logger.info("Loaded plist template from package resources")
+            
+            # Replace placeholders
+            plist_content = plist_content.replace("{START_SCRIPT_PATH}", start_script_path)
+            plist_content = plist_content.replace("{LOG_DIR}", os.path.join(voicemode_dir, 'logs'))
+            plist_content = plist_content.replace("{INSTALL_DIR}", install_dir)
             
             with open(plist_path, 'w') as f:
                 f.write(plist_content)
@@ -507,9 +414,8 @@ exec "$SERVER_BIN" \\
                 "start_script": start_script_path,
                 "message": f"Successfully installed whisper.cpp {current_version} with {gpu_type} support and whisper-server on port 2022{enable_message}{' (' + migration_msg + ')' if migration_msg else ''}"
             }
-        
-        # Install systemd service on Linux
         elif system == "Linux":
+            # Install systemd service on Linux
             logger.info("Installing systemd user service for whisper-server...")
             systemd_user_dir = os.path.expanduser("~/.config/systemd/user")
             os.makedirs(systemd_user_dir, exist_ok=True)
@@ -522,22 +428,22 @@ exec "$SERVER_BIN" \\
             service_path = os.path.join(systemd_user_dir, service_name)
             
             service_content = f"""[Unit]
-Description=Whisper.cpp Speech Recognition Server
-After=network.target
+    Description=Whisper.cpp Speech Recognition Server
+    After=network.target
 
-[Service]
-Type=simple
-ExecStart={start_script_path}
-Restart=on-failure
-RestartSec=10
-WorkingDirectory={install_dir}
-StandardOutput=append:{os.path.join(voicemode_dir, 'logs', 'whisper', 'whisper.out.log')}
-StandardError=append:{os.path.join(voicemode_dir, 'logs', 'whisper', 'whisper.err.log')}
-Environment="PATH=/usr/local/bin:/usr/bin:/bin:/usr/local/cuda/bin"
+    [Service]
+    Type=simple
+    ExecStart={start_script_path}
+    Restart=on-failure
+    RestartSec=10
+    WorkingDirectory={install_dir}
+    StandardOutput=append:{os.path.join(voicemode_dir, 'logs', 'whisper', 'whisper.out.log')}
+    StandardError=append:{os.path.join(voicemode_dir, 'logs', 'whisper', 'whisper.err.log')}
+    Environment="PATH=/usr/local/bin:/usr/bin:/bin:/usr/local/cuda/bin"
 
-[Install]
-WantedBy=default.target
-"""
+    [Install]
+    WantedBy=default.target
+    """
             
             with open(service_path, 'w') as f:
                 f.write(service_content)
@@ -572,49 +478,49 @@ WantedBy=default.target
             current_version = get_current_version(Path(install_dir))
             return {
                 "success": True,
-                "install_path": install_dir,
-                "model_path": model_path,
-                "gpu_enabled": use_gpu,
-                "gpu_type": gpu_type,
-                "version": current_version,
-                "performance_info": {
-                    "system": system,
-                    "gpu_acceleration": gpu_type,
-                    "model": model,
-                    "binary_path": main_path if 'main_path' in locals() else os.path.join(install_dir, "main"),
-                    "server_port": 2022,
-                    "server_url": "http://localhost:2022"
-                },
-                "systemd_service": service_path,
-                "systemd_enabled": systemd_enabled,
-                "start_script": start_script_path,
-                "message": f"Successfully installed whisper.cpp {current_version} with {gpu_type} support. {systemd_message}{enable_message}{' (' + migration_msg + ')' if migration_msg else ''}"
+            "install_path": install_dir,
+            "model_path": model_path,
+            "gpu_enabled": use_gpu,
+            "gpu_type": gpu_type,
+            "version": current_version,
+            "performance_info": {
+                "system": system,
+                "gpu_acceleration": gpu_type,
+                "model": model,
+                "binary_path": main_path if 'main_path' in locals() else os.path.join(install_dir, "main"),
+                "server_port": 2022,
+                "server_url": "http://localhost:2022"
+            },
+            "systemd_service": service_path,
+            "systemd_enabled": systemd_enabled,
+            "start_script": start_script_path,
+            "message": f"Successfully installed whisper.cpp {current_version} with {gpu_type} support. {systemd_message}{enable_message}{' (' + migration_msg + ')' if migration_msg else ''}"
             }
-        
+    
         else:
             # Handle auto_enable for other systems (if we add Windows support later)
             enable_message = ""
             if auto_enable is None:
-                auto_enable = SERVICE_AUTO_ENABLE
+              auto_enable = SERVICE_AUTO_ENABLE
             
             if auto_enable:
-                logger.info("Auto-enable not supported on this platform")
+              logger.info("Auto-enable not supported on this platform")
             
             current_version = get_current_version(Path(install_dir))
             return {
                 "success": True,
-                "install_path": install_dir,
-                "model_path": model_path,
-                "gpu_enabled": use_gpu,
-                "gpu_type": gpu_type,
-                "version": current_version,
-                "performance_info": {
-                    "system": system,
-                    "gpu_acceleration": gpu_type,
-                    "model": model,
-                    "binary_path": main_path if 'main_path' in locals() else os.path.join(install_dir, "main")
-                },
-                "message": f"Successfully installed whisper.cpp {current_version} with {gpu_type} support{enable_message}{' (' + migration_msg + ')' if migration_msg else ''}"
+            "install_path": install_dir,
+            "model_path": model_path,
+            "gpu_enabled": use_gpu,
+            "gpu_type": gpu_type,
+            "version": current_version,
+            "performance_info": {
+                "system": system,
+                "gpu_acceleration": gpu_type,
+                "model": model,
+                "binary_path": main_path if 'main_path' in locals() else os.path.join(install_dir, "main")
+            },
+            "message": f"Successfully installed whisper.cpp {current_version} with {gpu_type} support{enable_message}{' (' + migration_msg + ')' if migration_msg else ''}"
             }
         
     except subprocess.CalledProcessError as e:
@@ -631,4 +537,4 @@ WantedBy=default.target
         return {
             "success": False,
             "error": str(e)
-        }
+        }

{voice_mode-2.33.0.dist-info → voice_mode-2.33.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: voice-mode
-Version: 2.33.0
+Version: 2.33.3
 Summary: VoiceMode - Voice interaction capabilities for AI assistants (formerly voice-mcp)
 Project-URL: Homepage, https://github.com/mbailey/voicemode
 Project-URL: Repository, https://github.com/mbailey/voicemode
@@ -116,7 +116,15 @@ Natural voice conversations for AI assistants. Voice Mode brings human-like voic
 Install Claude Code with Voice Mode configured and ready to run on Linux, macOS, and Windows WSL:
 
 ```bash
+# Download and run the installer
 curl -O https://getvoicemode.com/install.sh && bash install.sh
+
+# While local voice services can be installed automatically, we recommend
+# providing an OpenAI API key as a fallback in case local services are unavailable
+export OPENAI_API_KEY=your-openai-key  # Optional but recommended
+
+# Start a voice conversation
+claude /voicemode:converse
 ```
 
 This installer will:
@@ -124,16 +132,7 @@ This installer will:
 - Install Claude Code if not already installed
 - Configure Voice Mode as an MCP server
 - Set up your system for voice conversations
-
-After installation, just run:
-```bash
-# With OpenAI API (cloud-based, requires API key)
-export OPENAI_API_KEY=your-openai-key
-claude /voicemode:converse
-
-# Or use free local services (Voice Mode will offer to install them)
-claude /voicemode:converse
-```
+- Offer to install free local STT/TTS services if no API key is provided
 
 ### Manual Installation
 
@@ -693,7 +692,7 @@ To save all audio files (both TTS output and STT input):
 export VOICEMODE_SAVE_AUDIO=true
 ```
 
-Audio files are saved to: `~/voicemode_audio/` with timestamps in the filename.
+Audio files are saved to: `~/.voicemode/audio/YYYY/MM/` with timestamps in the filename.
 
 ## Documentation