Metadata-Version: 2.4
Name: TranscribeNPy
Version: 1.0.5
Summary: A Python module for recorded audio transcription via Wispr with groq API
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: groq>=1.7.0
Dynamic: license-file

# TranscribeNPy
A python module for transcribing audio files to text via Groq's Whisper-Large-v3/Whisper-Large-v3-turbo

## Installation
```bash
pip install TranscribeNPy
```
or via UV:
```bash
uv add TranscribeNPy
```

## Usage
```python
from transcribenpy import transcribe
import os

API_KEY = os.environ.get("GROQ_API_KEY")
audio_path = "samples/audio.wav"

text = transcribe(API_KEY, audio_path, model="Precise")
print(text)
```

## Parameters

- `api_key` : String
    - Groq API Key
    - Required
- `filename` : String
    - Audio file path
    - Default: "samples/audio.wav"
- `model` : String
    - Model to use for transcription
    - Options: 
      - "Fast" / "Quick" / "Fastest" / "Turbo" -> "whisper-large-v3-turbo"
      - "Precise" / "Heavy" / "Slow" -> "whisper-large-v3"
    - Default: "Fast"
