voicepipe 0.1.0__tar.gz

voicepipe-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 DanLab
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

voicepipe-0.1.0/PKG-INFO

@@ -0,0 +1,207 @@
+Metadata-Version: 2.4
+Name: voicepipe
+Version: 0.1.0
+Summary: One-command STT + TTS for any app
+Author-email: DanLab <dan@danlab.dev>
+License: MIT
+Project-URL: Homepage, https://github.com/danlab-ai/voicepipe
+Project-URL: Documentation, https://voicepipe.readthedocs.io
+Project-URL: Repository, https://github.com/danlab-ai/voicepipe
+Project-URL: Issues, https://github.com/danlab-ai/voicepipe/issues
+Keywords: stt,tts,speech,voice,whisper,kittentts,ai
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.20.0
+Provides-Extra: kittentts
+Requires-Dist: kittentts; extra == "kittentts"
+Provides-Extra: gtts
+Requires-Dist: gtts; extra == "gtts"
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
+Requires-Dist: black>=23.0.0; extra == "dev"
+Requires-Dist: mypy>=1.0.0; extra == "dev"
+Requires-Dist: ruff>=0.1.0; extra == "dev"
+Dynamic: license-file
+
+# VoicePipe
+
+<p align="center">
+  <strong>One-command voice integration for any app</strong>
+</p>
+
+<p align="center">
+  <a href="https://pypi.org/project/voicepipe/">
+    <img src="https://img.shields.io/pypi/v/voicepipe.svg" alt="PyPI version">
+  </a>
+  <a href="https://pypi.org/project/voicepipe/">
+    <img src="https://img.shields.io/pypi/pyversions/voicepipe.svg" alt="Python versions">
+  </a>
+  <a href="https://github.com/danlab-ai/voicepipe/blob/main/LICENSE">
+    <img src="https://img.shields.io/github/license/danlab-ai/voicepipe.svg" alt="License">
+  </a>
+</p>
+
+---
+
+## Overview
+
+VoicePipe provides **one-command** STT (Speech-to-Text) + TTS (Text-to-Speech) for any application. 
+
+- **STT**: whisper.cpp - fastest local speech recognition
+- **TTS**: KittenTTS - smallest neural TTS (15-80MB)
+
+## Installation
+
+```bash
+pip install voicepipe
+```
+
+## Quick Start
+
+```python
+from voicepipe import VoicePipeline
+
+# Initialize (auto-downloads models)
+voice = VoicePipeline()
+
+# Speech to Text
+text = voice.speech_to_text("audio.wav")
+print(f"You said: {text}")
+
+# Text to Speech
+audio = voice.text_to_speech("Hello, world!")
+```
+
+## Requirements
+
+- Python 3.8+
+- FFmpeg (for audio processing)
+
+## Install FFmpeg
+
+**macOS:**
+```bash
+brew install ffmpeg
+```
+
+**Linux:**
+```bash
+sudo apt install ffmpeg
+```
+
+**Windows:**
+```powershell
+choco install ffmpeg
+```
+
+## Configuration
+
+```python
+voice = VoicePipeline(
+    stt_model="tiny",        # tiny, base, small
+    tts_model="nano",        # nano, micro, mini
+    tts_voice="Bella",       # 8 voices available
+    tts_speed=1.0,          # 0.5 - 2.0
+    language="en",           # or "auto"
+    cache_dir="~/.voicepipe" # model cache
+)
+```
+
+## Available Voices
+
+- Bella, Jasper, Luna, Bruno, Rosie, Hugo, Kiki, Leo
+
+## Models
+
+### STT (whisper.cpp)
+| Model | Size | RAM | Speed |
+|-------|------|-----|-------|
+| tiny | 75MB | ~500MB | 10x realtime |
+| base | 142MB | ~1GB | 5x realtime |
+| small | 466MB | ~2GB | 2x realtime |
+
+### TTS (KittenTTS)
+| Model | Size | Quality |
+|-------|------|---------|
+| nano | 15MB | Good |
+| micro | 40MB | Better |
+| mini | 80MB | Best |
+
+## Use Cases
+
+### Chatbot with Voice
+```python
+@app.post("/voice/chat")
+async def voice_chat(audio: bytes):
+    # Convert speech to text
+    text = voice.speech_to_text_bytes(audio)
+    
+    # Get chatbot response
+    response = await chatbot.chat(text)
+    
+    # Convert response to speech
+    audio_response = voice.text_to_speech(response)
+    
+    return {"audio": audio_response}
+```
+
+### Voice Assistant
+```python
+async def run_assistant():
+    while True:
+        # Continuously listen and respond
+        text = await voice.speech_to_text_async(microphone_stream)
+        response = await assistant.respond(text)
+        voice.text_to_speech(response, play=True)
+```
+
+## API Reference
+
+### VoicePipeline
+
+| Method | Description |
+|--------|-------------|
+| `speech_to_text(audio_path)` | Convert audio file to text |
+| `speech_to_text_bytes(audio_data)` | Convert raw audio to text |
+| `text_to_speech(text)` | Convert text to audio bytes |
+| `text_to_speech_file(text, path)` | Convert text to audio file |
+| `list_voices()` | Get available TTS voices |
+| `get_status()` | Get pipeline status |
+
+## Development
+
+```bash
+# Clone repository
+git clone https://github.com/danlab-ai/voicepipe.git
+cd voicepipe
+
+# Install in development mode
+pip install -e ".[dev]"
+
+# Run tests
+pytest
+
+# Format code
+black src/voicepipe
+ruff check src/voicepipe
+```
+
+## License
+
+MIT License - see [LICENSE](LICENSE)
+
+---
+
+<p align="center">
+  Built by <a href="https://danlab.dev">DanLab</a>
+</p>

voicepipe-0.1.0/README.md

@@ -0,0 +1,172 @@
+# VoicePipe
+
+<p align="center">
+  <strong>One-command voice integration for any app</strong>
+</p>
+
+<p align="center">
+  <a href="https://pypi.org/project/voicepipe/">
+    <img src="https://img.shields.io/pypi/v/voicepipe.svg" alt="PyPI version">
+  </a>
+  <a href="https://pypi.org/project/voicepipe/">
+    <img src="https://img.shields.io/pypi/pyversions/voicepipe.svg" alt="Python versions">
+  </a>
+  <a href="https://github.com/danlab-ai/voicepipe/blob/main/LICENSE">
+    <img src="https://img.shields.io/github/license/danlab-ai/voicepipe.svg" alt="License">
+  </a>
+</p>
+
+---
+
+## Overview
+
+VoicePipe provides **one-command** STT (Speech-to-Text) + TTS (Text-to-Speech) for any application. 
+
+- **STT**: whisper.cpp - fastest local speech recognition
+- **TTS**: KittenTTS - smallest neural TTS (15-80MB)
+
+## Installation
+
+```bash
+pip install voicepipe
+```
+
+## Quick Start
+
+```python
+from voicepipe import VoicePipeline
+
+# Initialize (auto-downloads models)
+voice = VoicePipeline()
+
+# Speech to Text
+text = voice.speech_to_text("audio.wav")
+print(f"You said: {text}")
+
+# Text to Speech
+audio = voice.text_to_speech("Hello, world!")
+```
+
+## Requirements
+
+- Python 3.8+
+- FFmpeg (for audio processing)
+
+## Install FFmpeg
+
+**macOS:**
+```bash
+brew install ffmpeg
+```
+
+**Linux:**
+```bash
+sudo apt install ffmpeg
+```
+
+**Windows:**
+```powershell
+choco install ffmpeg
+```
+
+## Configuration
+
+```python
+voice = VoicePipeline(
+    stt_model="tiny",        # tiny, base, small
+    tts_model="nano",        # nano, micro, mini
+    tts_voice="Bella",       # 8 voices available
+    tts_speed=1.0,          # 0.5 - 2.0
+    language="en",           # or "auto"
+    cache_dir="~/.voicepipe" # model cache
+)
+```
+
+## Available Voices
+
+- Bella, Jasper, Luna, Bruno, Rosie, Hugo, Kiki, Leo
+
+## Models
+
+### STT (whisper.cpp)
+| Model | Size | RAM | Speed |
+|-------|------|-----|-------|
+| tiny | 75MB | ~500MB | 10x realtime |
+| base | 142MB | ~1GB | 5x realtime |
+| small | 466MB | ~2GB | 2x realtime |
+
+### TTS (KittenTTS)
+| Model | Size | Quality |
+|-------|------|---------|
+| nano | 15MB | Good |
+| micro | 40MB | Better |
+| mini | 80MB | Best |
+
+## Use Cases
+
+### Chatbot with Voice
+```python
+@app.post("/voice/chat")
+async def voice_chat(audio: bytes):
+    # Convert speech to text
+    text = voice.speech_to_text_bytes(audio)
+    
+    # Get chatbot response
+    response = await chatbot.chat(text)
+    
+    # Convert response to speech
+    audio_response = voice.text_to_speech(response)
+    
+    return {"audio": audio_response}
+```
+
+### Voice Assistant
+```python
+async def run_assistant():
+    while True:
+        # Continuously listen and respond
+        text = await voice.speech_to_text_async(microphone_stream)
+        response = await assistant.respond(text)
+        voice.text_to_speech(response, play=True)
+```
+
+## API Reference
+
+### VoicePipeline
+
+| Method | Description |
+|--------|-------------|
+| `speech_to_text(audio_path)` | Convert audio file to text |
+| `speech_to_text_bytes(audio_data)` | Convert raw audio to text |
+| `text_to_speech(text)` | Convert text to audio bytes |
+| `text_to_speech_file(text, path)` | Convert text to audio file |
+| `list_voices()` | Get available TTS voices |
+| `get_status()` | Get pipeline status |
+
+## Development
+
+```bash
+# Clone repository
+git clone https://github.com/danlab-ai/voicepipe.git
+cd voicepipe
+
+# Install in development mode
+pip install -e ".[dev]"
+
+# Run tests
+pytest
+
+# Format code
+black src/voicepipe
+ruff check src/voicepipe
+```
+
+## License
+
+MIT License - see [LICENSE](LICENSE)
+
+---
+
+<p align="center">
+  Built by <a href="https://danlab.dev">DanLab</a>
+</p>

voicepipe-0.1.0/pyproject.toml

@@ -0,0 +1,69 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "voicepipe"
+version = "0.1.0"
+description = "One-command STT + TTS for any app"
+readme = "README.md"
+license = {text = "MIT"}
+authors = [
+    {name = "DanLab", email = "dan@danlab.dev"},
+]
+keywords = ["stt", "tts", "speech", "voice", "whisper", "kittentts", "ai"]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: MIT License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Topic :: Software Development :: Libraries :: Python Modules",
+]
+
+dependencies = [
+    "numpy>=1.20.0",
+]
+
+[project.optional-dependencies]
+kittentts = ["kittentts"]
+gtts = ["gtts"]
+dev = [
+    "pytest>=7.0.0",
+    "pytest-asyncio>=0.21.0",
+    "black>=23.0.0",
+    "mypy>=1.0.0",
+    "ruff>=0.1.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/danlab-ai/voicepipe"
+Documentation = "https://voicepipe.readthedocs.io"
+Repository = "https://github.com/danlab-ai/voicepipe"
+Issues = "https://github.com/danlab-ai/voicepipe/issues"
+
+[project.scripts]
+voicepipe = "voicepipe.cli:main"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+voicepipe = ["py.typed"]
+
+[tool.black]
+line-length = 100
+target-version = ["py38"]
+
+[tool.ruff]
+line-length = 100
+target-version = "py38"
+
+[tool.mypy]
+python_version = "3.8"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = false

voicepipe-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

voicepipe-0.1.0/src/voicepipe/__init__.py

@@ -0,0 +1,18 @@
+"""
+VoicePipe - Universal Voice Pipeline
+One-command STT + TTS for any app
+
+Install: pip install voicepipe
+Usage:
+    from voicepipe import VoicePipeline
+    voice = VoicePipeline()
+    text = voice.speech_to_text("audio.wav")
+    audio = voice.text_to_speech("Hello!")
+"""
+
+__version__ = "0.1.0"
+__author__ = "DanLab"
+
+from voicepipe.voice_pipeline import VoicePipeline
+
+__all__ = ["VoicePipeline", "__version__"]

voicepipe-0.1.0/src/voicepipe/audio.py

@@ -0,0 +1,156 @@
+"""
+Audio utilities for VoicePipe
+"""
+import subprocess
+import tempfile
+import os
+from pathlib import Path
+from typing import Optional
+
+
+class AudioUtils:
+    """Audio processing utilities."""
+    
+    @staticmethod
+    def convert_audio(
+        input_path: str,
+        output_path: str,
+        sample_rate: int = 16000,
+        mono: bool = True,
+        format: str = "wav",
+    ) -> str:
+        """
+        Convert audio file to different format.
+        
+        Args:
+            input_path: Input audio file
+            output_path: Output audio file
+            sample_rate: Target sample rate
+            mono: Convert to mono
+            format: Output format
+            
+        Returns:
+            Path to converted file
+        """
+        mono_arg = "-ac 1" if mono else ""
+        cmd = [
+            "ffmpeg", "-y",
+            "-i", input_path,
+            "-ar", str(sample_rate),
+            mono_arg,
+            f"-c:a", "pcm_s16le" if format == "wav" else format,
+            output_path,
+        ]
+        
+        result = subprocess.run(cmd, capture_output=True, text=True)
+        
+        if result.returncode != 0:
+            raise RuntimeError(f"Audio conversion failed: {result.stderr}")
+        
+        return output_path
+    
+    @staticmethod
+    def get_audio_duration(audio_path: str) -> float:
+        """Get duration of audio file in seconds."""
+        cmd = [
+            "ffprobe",
+            "-v", "error",
+            "-show_entries", "format=duration",
+            "-of", "default=noprint_wrappers=1:nokey=1",
+            audio_path,
+        ]
+        
+        result = subprocess.run(cmd, capture_output=True, text=True)
+        
+        if result.returncode != 0:
+            raise RuntimeError(f"Failed to get duration: {result.stderr}")
+        
+        return float(result.stdout.strip())
+    
+    @staticmethod
+    def normalize_audio(input_path: str, output_path: str) -> str:
+        """Normalize audio volume."""
+        cmd = [
+            "ffmpeg", "-y",
+            "-i", input_path,
+            "-af", "loudnorm=I=-16:TP=-1.5:LRA=11",
+            output_path,
+        ]
+        
+        result = subprocess.run(cmd, capture_output=True, text=True)
+        
+        if result.returncode != 0:
+            raise RuntimeError(f"Audio normalization failed: {result.stderr}")
+        
+        return output_path
+    
+    @staticmethod
+    def trim_silence(
+        input_path: str,
+        output_path: str,
+        threshold: float = -40,
+        min_duration: float = 0.5,
+    ) -> str:
+        """Trim silence from audio."""
+        cmd = [
+            "ffmpeg", "-y",
+            "-i", input_path,
+            "-af", f"silenceremove=start_periods=1:start_duration={min_duration}:start_threshold={threshold}dB:detection=speech",
+            output_path,
+        ]
+        
+        result = subprocess.run(cmd, capture_output=True, text=True)
+        
+        if result.returncode != 0:
+            raise RuntimeError(f"Silence trim failed: {result.stderr}")
+        
+        return output_path
+    
+    @staticmethod
+    def split_stereo(input_path: str) -> tuple:
+        """Split stereo audio to two mono files."""
+        left_path = input_path.replace(".wav", "_left.wav")
+        right_path = input_path.replace(".wav", "_right.wav")
+        
+        # Left channel
+        subprocess.run([
+            "ffmpeg", "-y", "-i", input_path,
+            "-af", "pan=mono|c0=c0",
+            left_path
+        ], capture_output=True)
+        
+        # Right channel
+        subprocess.run([
+            "ffmpeg", "-y", "-i", input_path,
+            "-af", "pan=mono|c0=c1",
+            right_path
+        ], capture_output=True)
+        
+        return left_path, right_path
+    
+    @staticmethod
+    def concatenate_audio(audio_files: list, output_path: str) -> str:
+        """Concatenate multiple audio files."""
+        # Create file list
+        with tempfile.NamedTemporaryFile(mode='w', suffix=".txt", delete=False) as f:
+            for audio_file in audio_files:
+                f.write(f"file '{audio_file}'\n")
+            list_path = f.name
+        
+        cmd = [
+            "ffmpeg", "-y",
+            "-f", "concat",
+            "-safe", "0",
+            "-i", list_path,
+            "-c", "copy",
+            output_path,
+        ]
+        
+        result = subprocess.run(cmd, capture_output=True, text=True)
+        
+        os.unlink(list_path)
+        
+        if result.returncode != 0:
+            raise RuntimeError(f"Audio concatenation failed: {result.stderr}")
+        
+        return output_path