Metadata-Version: 2.4
Name: pyrospeak
Version: 0.0.1
Summary: Simple TTS & STT wrapper with multiple engines
Author: Mureșan Robert
License: MIT
Project-URL: Homepage, https://github.com/Robertinoos13/PyroSpeak-Library
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: pyttsx3
Requires-Dist: gTTS
Requires-Dist: pygame
Requires-Dist: numpy
Requires-Dist: sounddevice
Requires-Dist: whisper
Requires-Dist: faststt
Requires-Dist: elevenlabs

# `PyroSpeak` 🗣️

`PyroSpeak` is a simple and flexible Python library for Text-to-Speech (TTS) and Speech-to-Text (STT), designed to work with multiple engines, both online and offline, using a clean and beginner-friendly API.

It aims to provide a single, unified interface for common speech tasks without forcing you to deal with low-level audio details.

## Features

- Multiple TTS engines (online & offline)
- Multiple STT engines (FastSTT, Whisper)
- Minimal and intuitive API
- Suitable for experiments, bots, and small AI projects
- Works well with real-time audio

## Quick Example
``` python
from pyrospeak import speak, record

# Text to Speech
speak("Hello world!", engine="gtts")

# Speech to Text
text = record(engine="whisper")
print(text)
```

## Supported Engines
### Text-to-Speech (TTS)

- gTTS (Google Text-to-Speech)
- pyttsx3 (offline)
- ElevenLabs (API-based)

### Speech-to-Text (STT)

- FastSTT
- Whisper (OpenAI)

---

## Configuration

Most functions are configurable through keyword arguments such as:
- engine
- language
- model size / device
- time limits

Refer to the source code for full parameter lists.


## License

MIT License

