abstractvoice 0.1.1__py3-none-any.whl → 0.2.1__py3-none-any.whl

{abstractvoice-0.1.1.dist-info → abstractvoice-0.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: abstractvoice
-Version: 0.1.1
+Version: 0.2.1
 Summary: A modular Python library for voice interactions with AI systems
 Author-email: Laurent-Philippe Albou <contact@abstractcore.ai>
 License-Expression: MIT
@@ -18,31 +18,76 @@ Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy>=1.24.0
-Requires-Dist: sounddevice>=0.4.6
-Requires-Dist: webrtcvad>=2.0.10
-Requires-Dist: PyAudio>=0.2.13
-Requires-Dist: openai-whisper>=20230314
-Requires-Dist: coqui-tts>=0.27.0
-Requires-Dist: torch>=2.0.0
-Requires-Dist: torchaudio>=2.0.0
-Requires-Dist: librosa>=0.10.0
-Requires-Dist: soundfile>=0.12.1
 Requires-Dist: requests>=2.31.0
-Requires-Dist: flask>=2.0.0
-Requires-Dist: tiktoken>=0.6.0
+Provides-Extra: voice
+Requires-Dist: sounddevice>=0.4.6; extra == "voice"
+Requires-Dist: webrtcvad>=2.0.10; extra == "voice"
+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: librosa<0.11.0,>=0.10.0; extra == "tts"
+Provides-Extra: stt
+Requires-Dist: openai-whisper>=20230314; extra == "stt"
+Requires-Dist: tiktoken>=0.6.0; extra == "stt"
+Provides-Extra: web
+Requires-Dist: flask>=2.0.0; extra == "web"
+Provides-Extra: all
+Requires-Dist: sounddevice>=0.4.6; extra == "all"
+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: librosa<0.11.0,>=0.10.0; extra == "all"
+Requires-Dist: soundfile>=0.12.1; extra == "all"
+Requires-Dist: flask>=2.0.0; extra == "all"
+Requires-Dist: tiktoken>=0.6.0; extra == "all"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: black>=22.0.0; extra == "dev"
 Requires-Dist: flake8>=5.0.0; extra == "dev"
+Provides-Extra: voice-full
+Requires-Dist: sounddevice>=0.4.6; extra == "voice-full"
+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: librosa<0.11.0,>=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: librosa<0.11.0,>=0.10.0; extra == "core-tts"
+Provides-Extra: core-stt
+Requires-Dist: openai-whisper>=20230314; extra == "core-stt"
+Requires-Dist: tiktoken>=0.6.0; extra == "core-stt"
+Provides-Extra: audio-only
+Requires-Dist: sounddevice>=0.4.6; extra == "audio-only"
+Requires-Dist: webrtcvad>=2.0.10; extra == "audio-only"
+Requires-Dist: PyAudio>=0.2.13; extra == "audio-only"
+Requires-Dist: soundfile>=0.12.1; extra == "audio-only"
 Dynamic: license-file
 
 # AbstractVoice
 
 [![PyPI version](https://img.shields.io/pypi/v/abstractvoice.svg)](https://pypi.org/project/abstractvoice/)
 [![Python Version](https://img.shields.io/pypi/pyversions/abstractvoice)](https://pypi.org/project/abstractvoice/)
-[![License](https://img.shields.io/pypi/l/abstractvoice)](https://github.com/lpalbou/abstractvoice/blob/main/LICENSE)
+[![license](https://img.shields.io/github/license/lpalbou/AbstractVoice)](https://github.com/lpalbou/abstractvoice/blob/main/LICENSE)
 [![GitHub stars](https://img.shields.io/github/stars/lpalbou/abstractvoice?style=social)](https://github.com/lpalbou/abstractvoice/stargazers)
 
+
 A modular Python library for voice interactions with AI systems, providing text-to-speech (TTS) and speech-to-text (STT) capabilities with interrupt handling.
 
 While we provide CLI and WEB examples, AbstractVoice is designed to be integrated in other projects.
@@ -62,73 +107,174 @@ While we provide CLI and WEB examples, AbstractVoice is designed to be integrate
 - **Interrupt Handling**: Stop TTS by speaking or using stop commands
 - **Modular Design**: Easily integrate with any text generation system
 
+Note : *the LLM access is rudimentary and abstractvoice is provided more as an example and demonstrator. A better integration is to use the functionalities of this library and use them directly in combination with [AbstractCore](https://github.com/lpalbou/AbstractCore)*.
+
 ## Installation
 
-### Prerequisites
+AbstractVoice is designed to **work everywhere, out of the box** with automatic quality upgrades.
+
+### 🚀 Quick Start (Recommended)
+
+```bash
+# One command installation - works on all systems
+pip install abstractvoice[all]
+
+# Verify it works
+python -c "from abstractvoice import VoiceManager; print('✅ Ready to go!')"
+```
 
-- Python 3.8+ (3.11+ recommended)
-- PortAudio for audio input/output
-- **Recommended**: espeak-ng for best voice quality (VITS model)
+**That's it!** AbstractVoice automatically:
+- ✅ **Works everywhere** - Uses reliable models that run on any system
+- ✅ **Auto-upgrades quality** - Detects when better models are available
+- ✅ **No system dependencies required** - Pure Python installation
+- ✅ **Optional quality boost** - Install `espeak-ng` for premium voices
 
-### Basic Installation
+### Installation Options
 
 ```bash
-# Install from PyPI
+# Minimal (just 2 dependencies)
 pip install abstractvoice
 
-# Or clone the repository
-git clone https://github.com/lpalbou/abstractvoice.git
-cd abstractvoice
-pip install -e .
+# Add features as needed
+pip install abstractvoice[tts]      # Text-to-speech
+pip install abstractvoice[stt]      # Speech-to-text
+pip install abstractvoice[all]      # Everything (recommended)
+
+# Language-specific
+pip install abstractvoice[fr]       # French with all features
+pip install abstractvoice[de]       # German with all features
 ```
 
-### Development Installation
+### Optional Quality Upgrade
+
+For the **absolute best voice quality**, install espeak-ng:
 
 ```bash
-# Install with development dependencies
-pip install "abstractvoice[dev]"
+# macOS
+brew install espeak-ng
+
+# Linux
+sudo apt-get install espeak-ng
+
+# Windows
+conda install espeak-ng
 ```
 
-### From Requirements File
+AbstractVoice automatically detects espeak-ng and upgrades to premium quality voices when available.
 
-```bash
-# Install all dependencies including the package
-pip install -r requirements.txt
+## Quick Start
+
+### Basic Usage (Minimal Installation)
+
+```python
+# First install with minimal dependencies
+# pip install abstractvoice
+
+from abstractvoice import VoiceManager
+
+# This will show a helpful error message with installation instructions
+try:
+    vm = VoiceManager()
+except ImportError as e:
+    print(e)  # Shows: "TTS functionality requires optional dependencies..."
+    # Follow the instructions to install: pip install abstractvoice[all]
 ```
 
-### Installing espeak-ng (Recommended for Best Quality)
+### Full Usage Example
 
-AbstractVoice will work without espeak-ng, but voice quality will be significantly better with it:
+```python
+# After installing with: pip install abstractvoice[all]
 
-**macOS:**
-```bash
-brew install espeak-ng
+from abstractvoice import VoiceManager
+
+# Initialize voice manager
+vm = VoiceManager(language='en', debug_mode=True)
+
+# Text-to-speech
+vm.speak("Hello! I can speak text and listen for responses.")
+
+# Speech-to-text with callbacks
+def on_transcription(text):
+    print(f"You said: {text}")
+    # Process the transcription
+    vm.speak(f"I heard you say: {text}")
+
+def on_stop():
+    print("Stopping voice interaction")
+
+# Start listening
+vm.listen(on_transcription, on_stop)
+
+# The voice manager will automatically pause listening when speaking
+# and resume when done to prevent feedback loops
 ```
 
-**Linux (Ubuntu/Debian):**
-```bash
-sudo apt-get install espeak-ng
+## Additional Examples
+
+### Language-Specific Usage
+
+```python
+# French voice
+vm_fr = VoiceManager(language='fr')
+vm_fr.speak("Bonjour! Je peux parler français.")
+
+# Spanish voice
+vm_es = VoiceManager(language='es')
+vm_es.speak("¡Hola! Puedo hablar español.")
+
+# Dynamic language switching
+vm.set_language('fr')  # Switch to French
+vm.set_language('en')  # Switch back to English
 ```
 
-**Linux (Fedora/RHEL):**
-```bash
-sudo yum install espeak-ng
+### Advanced Configuration
+
+```python
+from abstractvoice import VoiceManager
+
+# Custom TTS model selection
+vm = VoiceManager(
+    language='en',
+    tts_model='tts_models/en/ljspeech/fast_pitch',  # Specific model
+    whisper_model='base',  # Larger Whisper model for better accuracy
+    debug_mode=True
+)
+
+# Speed control
+vm.set_speed(1.5)  # 1.5x speed
+vm.speak("This text will be spoken faster.")
+
+# Model switching at runtime
+vm.set_tts_model('tts_models/en/ljspeech/vits')  # Switch to VITS
+vm.set_whisper('small')  # Switch to larger Whisper model
 ```
 
-**Windows:**
-```bash
-# Option 1: Using Conda
-conda install -c conda-forge espeak-ng
+### Error Handling and Graceful Degradation
 
-# Option 2: Using Chocolatey
-choco install espeak-ng
+AbstractVoice is designed to provide helpful error messages and fallback gracefully:
+
+```python
+# If you install just the basic package
+# pip install abstractvoice
 
-# Option 3: Download installer from https://github.com/espeak-ng/espeak-ng/releases
+from abstractvoice import VoiceManager  # This works fine
+
+try:
+    vm = VoiceManager()  # This will fail with helpful message
+except ImportError as e:
+    print(e)
+    # Output: "TTS functionality requires optional dependencies. Install with:
+    #          pip install abstractvoice[tts]    # For TTS only
+    #          pip install abstractvoice[all]    # For all features"
+
+# Missing espeak-ng automatically falls back to compatible models
+# Missing dependencies show clear installation instructions
+# All errors are graceful with helpful guidance
 ```
 
-**Without espeak-ng:** AbstractVoice will automatically fall back to a simpler TTS model (fast_pitch) that works everywhere but has lower voice quality.
+## CLI and Web Examples
 
-## Quick Start
+AbstractVoice includes example applications to demonstrate its capabilities:
 
 ### Using AbstractVoice from the Command Line
 

abstractvoice-0.2.1.dist-info/RECORD

@@ -0,0 +1,21 @@
+abstractvoice/__init__.py,sha256=6GWG6ruCOQ73dOK1-lGB4F8fvjoAtsAP8fIoYCnVuZk,817
+abstractvoice/__main__.py,sha256=e6jhoONg3uwwPUCdnr68bSRTT1RrpWy2DrOJ6ozMJVc,4775
+abstractvoice/dependency_check.py,sha256=BUUADz4un4_FCZzNpgwk1qpJ6yqVi5Pvjfd3JLS8hAI,10045
+abstractvoice/recognition.py,sha256=4KtDUDFixEYuBUMDH2fWaD9csKlwA9tqXkMAkyQMSMo,11259
+abstractvoice/voice_manager.py,sha256=WYuN949pzf4pw8SE3g40OQZNC1CbgUZ5SzvpAGAIfPI,29995
+abstractvoice/examples/__init__.py,sha256=94vpKJDlfOrEBIUETg-57Q5Z7fYDidg6v4UzV7V_lZA,60
+abstractvoice/examples/cli_repl.py,sha256=uRFqUOVDP6RXrMquB_rQ1_fxdyLn_UHwuiu30XHbYwE,41250
+abstractvoice/examples/voice_cli.py,sha256=mhiO7i0AooPWPZD-K6O-wQUvMFbRFED-dlGNUjDvsUE,3962
+abstractvoice/examples/web_api.py,sha256=0g5LKJpl7fZepPQJL25AcdaevV-xv34VqqyWGYYchPk,6376
+abstractvoice/stt/__init__.py,sha256=PFc6la3tTkxT4TJYwb0PnMIahM_hFtU4pNQdeKmbooo,120
+abstractvoice/stt/transcriber.py,sha256=GdaH1OsCHu4Vu9rUsQlzH6X9bfcnoiK5tGz1AW_uj6Q,5481
+abstractvoice/tts/__init__.py,sha256=WgJrxqdc_qaRyfFt1jbgMQD9S757jYuBpDzMRB02TFs,122
+abstractvoice/tts/tts_engine.py,sha256=9CZAZITZ_VNZs0grwsqWIFj3aUsHvrWeFVV66lH_Bf8,44926
+abstractvoice/vad/__init__.py,sha256=RIIbFw25jNHgel06E4VvTWJnXjwjeFZ98m1Vx9hVjuo,119
+abstractvoice/vad/voice_detector.py,sha256=ghrhpDFlIR5TsMB2gpigXY6t5c_1yZ7vEX1imAMgWjc,3166
+abstractvoice-0.2.1.dist-info/licenses/LICENSE,sha256=TiDPM5WcFRQPoC5e46jGMeMppZ-eu0eFx_HytjE49bk,1105
+abstractvoice-0.2.1.dist-info/METADATA,sha256=KFp786KB4_KECTUvlTdWgvLkiTPXhrHhJup9huRAESs,37533
+abstractvoice-0.2.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+abstractvoice-0.2.1.dist-info/entry_points.txt,sha256=rL63lqtLrbd7w_hGsR_w9Mr5baq4p3Mzwn4_UJqR_nI,120
+abstractvoice-0.2.1.dist-info/top_level.txt,sha256=a1qyxqgF1O8cJtPKpcJuImGZ_uXqPNghbLZ9gp-UiOo,14
+abstractvoice-0.2.1.dist-info/RECORD,,

{abstractvoice-0.1.1.dist-info → abstractvoice-0.2.1.dist-info}/licenses/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2025 Laurent-Philippe Albou (lpalbou@gmail.com)
+Copyright (c) 2025 Laurent-Philippe Albou (contact@abstractcore.ai)
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

abstractvoice-0.1.1.dist-info/RECORD

@@ -1,20 +0,0 @@
-abstractvoice/__init__.py,sha256=6GWG6ruCOQ73dOK1-lGB4F8fvjoAtsAP8fIoYCnVuZk,817
-abstractvoice/__main__.py,sha256=ZACGwnSWpqyjQ4oDj6IMj0hV8w76UCST5ZVZa8NMdNY,3546
-abstractvoice/recognition.py,sha256=dWAZ-Pxk0GrDurfTEuDRd5f5DjRYq_68qffUMyr0IvY,9487
-abstractvoice/voice_manager.py,sha256=fDDWAXY6K8wv51JFdLfEDR5-1TW8gevFNY7czyMx4FA,9049
-abstractvoice/examples/__init__.py,sha256=94vpKJDlfOrEBIUETg-57Q5Z7fYDidg6v4UzV7V_lZA,60
-abstractvoice/examples/cli_repl.py,sha256=_Pvp6dSkdJz8csQ3YvVAyAOuI3t0GYdp6_2L3uftC4A,33363
-abstractvoice/examples/voice_cli.py,sha256=M3Gf7CN3XJJkIcILfj5141SAMVCCie7yjG_fwHjbiDA,3141
-abstractvoice/examples/web_api.py,sha256=0g5LKJpl7fZepPQJL25AcdaevV-xv34VqqyWGYYchPk,6376
-abstractvoice/stt/__init__.py,sha256=PFc6la3tTkxT4TJYwb0PnMIahM_hFtU4pNQdeKmbooo,120
-abstractvoice/stt/transcriber.py,sha256=DhCT3yXdWr0dsD7ciT2tIa6XAHrIe3ZvuwK8S7pUM2Y,4845
-abstractvoice/tts/__init__.py,sha256=WgJrxqdc_qaRyfFt1jbgMQD9S757jYuBpDzMRB02TFs,122
-abstractvoice/tts/tts_engine.py,sha256=cuoKaMw7MP2PyUFE0LwZZqYI8tcIGIiX2ZzSP1QH4qo,39224
-abstractvoice/vad/__init__.py,sha256=RIIbFw25jNHgel06E4VvTWJnXjwjeFZ98m1Vx9hVjuo,119
-abstractvoice/vad/voice_detector.py,sha256=fR7uNuDVx_0vLzcMa8d1cEYtyAeZ1nW9ao5_V57rW7s,2584
-abstractvoice-0.1.1.dist-info/licenses/LICENSE,sha256=jxyvKKcODBeM8o4aaTjVpeSI74XSjS4zwIu_n-8eNNE,1099
-abstractvoice-0.1.1.dist-info/METADATA,sha256=DJFMbqivew2GBq6uc4sFrEhjBTaIIBKq0lxlKOmFITo,31804
-abstractvoice-0.1.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-abstractvoice-0.1.1.dist-info/entry_points.txt,sha256=rL63lqtLrbd7w_hGsR_w9Mr5baq4p3Mzwn4_UJqR_nI,120
-abstractvoice-0.1.1.dist-info/top_level.txt,sha256=a1qyxqgF1O8cJtPKpcJuImGZ_uXqPNghbLZ9gp-UiOo,14
-abstractvoice-0.1.1.dist-info/RECORD,,