Metadata-Version: 2.4
Name: audiopod
Version: 1.2.0
Summary: Professional Audio Processing API Client for Python
Home-page: https://github.com/audiopod-ai/audiopod-python
Author: AudioPod AI
Author-email: AudioPod AI <support@audiopod.ai>
Project-URL: Homepage, https://audiopod.ai
Project-URL: Repository, https://github.com/audiopod-ai/audiopod
Project-URL: Bug Tracker, https://github.com/audiopod-ai/audiopod/issues
Project-URL: API Reference, https://docs.audiopod.ai/
Keywords: audio,processing,ai,voice,cloning,transcription,translation,music,generation,denoising,api,sdk
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: Operating System :: OS Independent
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: Programming Language :: Python :: 3.12
Classifier: Topic :: Multimedia :: Sound/Audio
Classifier: Topic :: Multimedia :: Sound/Audio :: Analysis
Classifier: Topic :: Multimedia :: Sound/Audio :: Conversion
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: requests>=2.28.0
Requires-Dist: aiohttp>=3.8.0
Requires-Dist: pydantic>=1.10.0
Requires-Dist: python-dotenv>=0.19.0
Requires-Dist: tqdm>=4.64.0
Requires-Dist: websockets>=10.4
Requires-Dist: click>=8.0.0
Provides-Extra: dev
Requires-Dist: pytest>=7.0.0; extra == "dev"
Requires-Dist: pytest-asyncio>=0.21.0; extra == "dev"
Requires-Dist: black>=22.0.0; extra == "dev"
Requires-Dist: flake8>=5.0.0; extra == "dev"
Requires-Dist: mypy>=0.991; extra == "dev"
Requires-Dist: twine>=4.0.0; extra == "dev"
Requires-Dist: build>=0.10.0; extra == "dev"
Provides-Extra: docs
Requires-Dist: sphinx>=5.0.0; extra == "docs"
Requires-Dist: sphinx-rtd-theme>=1.2.0; extra == "docs"
Requires-Dist: sphinx-autodoc-typehints>=1.19.0; extra == "docs"
Dynamic: author
Dynamic: home-page
Dynamic: license-file
Dynamic: requires-python

# AudioPod Python SDK

The official Python SDK for the AudioPod API - Professional Audio Processing powered by AI.

[![PyPI version](https://badge.fury.io/py/audiopod.svg)](https://badge.fury.io/py/audiopod)
[![Python 3.8+](https://img.shields.io/badge/python-3.8+-blue.svg)](https://www.python.org/downloads/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

## Features

- 🎵 **Music Generation** - Create music from text prompts, lyrics, or audio samples
- 🎤 **Voice Cloning** - Clone voices from audio samples and generate speech
- 📝 **Transcription** - Convert speech to text with speaker diarization
- 🌍 **Translation** - Translate audio and video content between languages
- 🎬 **Karaoke Generation** - Create karaoke videos with synchronized lyrics
- 🔊 **Audio Enhancement** - Denoise and improve audio quality
- 👥 **Speaker Analysis** - Identify and separate speakers in audio
- 💰 **Credit Management** - Track usage and manage API credits

## Installation

```bash
pip install audiopod
```

## Quick Start

### Authentication

Get your API key from the [AudioPod Dashboard](https://app.audiopod.ai/dashboard) and set it as an environment variable:

```bash
export AUDIOPOD_API_KEY="ap_your_api_key_here"
```

Or pass it directly to the client:

```python
import audiopod

client = audiopod.Client(api_key="ap_your_api_key_here")
```

### Basic Usage

#### Voice Generation (Unified TTS & Cloning)

```python
import audiopod

# Initialize client
client = audiopod.Client()

# Generate voice using file cloning (unified approach)
job = client.voice.generate_voice(
    text="Hello! This is voice generation using a cloned voice.",
    voice_file="path/to/voice_sample.wav",  # For voice cloning
    language="en",
    audio_format="mp3",
    generation_params={
        "speed": 1.0
    },
    wait_for_completion=True
)

print(f"Generated audio URL: {job.output_url}")

# Generate speech with existing voice profile (unified approach)
speech = client.voice.generate_voice(
    text="Hello from my voice profile!",
    voice_id="voice-profile-id",  # For existing voice profiles
    language="en",
    audio_format="mp3",
    generation_params={
        "speed": 1.0
    },
    wait_for_completion=True
)

# Backward compatibility methods (deprecated - use generate_voice instead)
legacy_clone = client.voice.clone_voice(
    voice_file="path/to/voice_sample.wav",
    text="Hello! This is a cloned voice speaking.",
    language="en",
    wait_for_completion=True
)
```

#### Music Generation

```python
# Generate music from text
music_job = client.music.generate_music(
    prompt="upbeat electronic dance music with heavy bass",
    duration=120.0,  # 2 minutes
    wait_for_completion=True
)

print(f"Generated music URL: {music_job.output_url}")
```

#### Audio Transcription

```python
# Transcribe audio with speaker diarization
transcript = client.transcription.transcribe_audio(
    audio_file="path/to/audio.mp3",
    language="en",
    enable_speaker_diarization=True,
    wait_for_completion=True
)

print(f"Transcript: {transcript.transcript}")
print(f"Detected {len(transcript.segments)} speakers")
```

#### Speech-to-Speech Translation

```python
# Translate speech while preserving voice characteristics
translation = client.translation.translate_speech(
    audio_file="path/to/english_audio.wav",
    target_language="es",  # Spanish
    source_language="en",  # English (optional - auto-detect)
    wait_for_completion=True
)

print(f"Translated audio URL: {translation.translated_audio_url}")

# Or translate from URL
url_translation = client.translation.translate_speech(
    url="https://example.com/audio.mp3",
    target_language="fr",  # French
    wait_for_completion=True
)
```

### Async Support

The SDK supports async/await for better performance:

```python
import asyncio
import audiopod

async def main():
    async with audiopod.AsyncClient() as client:
        # All the same methods are available with async support
        job = await client.voice.clone_voice(
            voice_file="voice.wav",
            text="Async voice cloning!",
            wait_for_completion=True
        )
        print(f"Async result: {job['output_url']}")

asyncio.run(main())
```

### Advanced Examples

#### Create Voice Profile for Reuse

```python
# Create a reusable voice profile
voice_profile = client.voice.create_voice_profile(
    name="My Custom Voice",
    voice_file="voice_sample.wav",
    description="A professional voice for narration",
    wait_for_completion=True
)

# Use the voice profile for speech generation (unified approach - recommended)
speech = client.voice.generate_voice(
    text="This uses my custom voice profile with the unified method!",
    voice_id=voice_profile.id,
    language="en",
    audio_format="mp3",
    generation_params={
        "speed": 1.0
    },
    wait_for_completion=True
)

# Legacy method (still works - uses generate_voice internally)
legacy_speech = client.voice.generate_speech(
    voice_id=voice_profile.id,
    text="This uses the legacy method.",
    wait_for_completion=True
)
```

#### Batch Processing

```python
# Process multiple files
audio_files = ["file1.mp3", "file2.wav", "file3.m4a"]
jobs = []

for audio_file in audio_files:
    job = client.transcription.transcribe_audio(
        audio_file=audio_file,
        language="en"
    )
    jobs.append(job)

# Wait for all jobs to complete
for job in jobs:
    completed_job = client.transcription.get_transcription_job(job.id)
    while completed_job.job.status != "completed":
        time.sleep(5)
        completed_job = client.transcription.get_transcription_job(job.id)
    
    print(f"Transcript for {job.id}: {completed_job.transcript}")
```

#### Music Generation with Custom Parameters

```python
# Generate rap music with specific parameters
rap_job = client.music.generate_rap(
    lyrics="""
    Started from the bottom now we're here
    Building dreams with every single year
    AI music generation so clear
    AudioPod making magic appear
    """,
    style="modern",
    tempo=120,
    wait_for_completion=True
)

# Share the generated music
share_result = client.music.share_music_track(
    job_id=rap_job.job.id,
    platform="social",
    message="Check out this AI-generated rap!"
)
print(f"Shareable URL: {share_result['share_url']}")
```

#### Karaoke Video Generation

```python
# Generate karaoke video from YouTube URL
karaoke_job = client.karaoke.generate_karaoke(
    youtube_url="https://www.youtube.com/watch?v=example",
    video_style="modern",
    wait_for_completion=True
)

print(f"Karaoke video URL: {karaoke_job.result['karaoke_video_path']}")
```

## Error Handling

```python
import audiopod
from audiopod.exceptions import (
    AudioPodError,
    AuthenticationError,
    RateLimitError,
    ValidationError,
    ProcessingError
)

try:
    client = audiopod.Client(api_key="invalid_key")
    job = client.voice.clone_voice("voice.wav", "Test text")
    
except AuthenticationError:
    print("Invalid API key")
except RateLimitError as e:
    print(f"Rate limit exceeded. Retry after: {e.retry_after} seconds")
except ValidationError as e:
    print(f"Invalid input: {e.message}")
except ProcessingError as e:
    print(f"Processing failed: {e.message}")
except AudioPodError as e:
    print(f"General API error: {e.message}")
```

## Credit Management

```python
# Check credit balance
credits = client.credits.get_credit_balance()
print(f"Available credits: {credits.total_available_credits}")
print(f"Next reset: {credits.next_reset_date}")

# Get usage history
usage = client.credits.get_usage_history()
for record in usage:
    print(f"Service: {record['service_type']}, Credits: {record['credits_used']}")

# Get credit multipliers
multipliers = client.credits.get_credit_multipliers()
print(f"Voice cloning: {multipliers['voice_cloning']} credits/second")
```

## Configuration

### Environment Variables

- `AUDIOPOD_API_KEY`: Your AudioPod API key
- `AUDIOPOD_BASE_URL`: Custom API base URL (optional)
- `AUDIOPOD_TIMEOUT`: Request timeout in seconds (default: 30)

### Client Configuration

```python
client = audiopod.Client(
    api_key="your_api_key",
    base_url="https://api.audiopod.ai",  # Custom base URL
    timeout=60,  # 60 second timeout
    max_retries=5,  # Retry failed requests
    verify_ssl=True,  # SSL verification
    debug=True  # Enable debug logging
)
```

## API Reference

### Client Classes

- `audiopod.Client`: Synchronous client
- `audiopod.AsyncClient`: Asynchronous client

### Services

- `client.voice`: **Voice generation operations** (unified TTS & cloning using `generate_voice()`)
- `client.music`: Music generation and editing
- `client.transcription`: Speech-to-text transcription
- `client.translation`: Audio/video translation
- `client.speaker`: Speaker analysis and diarization  
- `client.denoiser`: Audio denoising and enhancement
- `client.karaoke`: Karaoke video generation
- `client.credits`: Credit management and usage tracking

#### Voice Service Methods

**Recommended (Unified Approach):**
- `client.voice.generate_voice()` - Generate speech with voice file (cloning) or voice ID (TTS)

**Legacy Methods (Backward Compatibility):**
- `client.voice.clone_voice()` - Clone voice from audio file (deprecated, uses `generate_voice` internally)
- `client.voice.generate_speech()` - Generate speech with voice profile (deprecated, uses `generate_voice` internally)

**Voice Management:**
- `client.voice.create_voice_profile()` - Create reusable voice profiles
- `client.voice.list_voice_profiles()` - List available voice profiles
- `client.voice.delete_voice_profile()` - Delete voice profiles

### Models

- `Job`: Base job information and status
- `VoiceProfile`: Voice profile details
- `TranscriptionResult`: Transcription results and metadata
- `MusicGenerationResult`: Music generation results
- `TranslationResult`: Translation job results
- `CreditInfo`: User credit information

## CLI Usage

The SDK includes a command-line interface:

```bash
# Check API status
audiopod health

# Get credit balance  
audiopod credits balance

# Clone a voice
audiopod voice clone voice.wav "Hello world!" --language en

# Generate music
audiopod music generate "upbeat electronic music" --duration 60

# Transcribe audio
audiopod transcription transcribe audio.mp3 --language en
```

## Requirements

- Python 3.8+
- Active AudioPod account with API access
- Valid API key

## Support

- 📖 [API Reference](https://docs.audiopod.ai)
- 💬 [Discord Community](https://discord.gg/audiopod)
- 📧 [Email Support](mailto:support@audiopod.ai)
- 🐛 [Bug Reports](https://github.com/AudiopodAI/audiopod)

## License

This SDK is released under the MIT License. See [LICENSE](LICENSE) for details.

---

Made with ❤️ by the AudioPod team
