Realtimetts

**Enhancements & Changes:**
- Refactored module initialization for on-demand engine loading.
- Reduced initial import time with lazy loading.
- Clearer error messages with installation hints for missing dependencies.

- **Enhanced OpenAI Engine Initialization:**
- Added optional parameters: `instructions`, `debug`, `speed`, `response_format`, and `timeout`.
- Updated available voices to include "ash", "coral", and "sage".
- **Note:** The `speed` and `timeout` parameters are not working at the moment; unclear why - they are being submitted to the API.

- **Text-to-Stream Improvements:**
- Introduced an `error_flag` to track errors during playback.
- Set the synthesis worker thread as daemon to ensure proper thread termination.

- **Dependency Update:**
- Upgraded the OpenAI package from version 1.66.3 to 1.68.2.

**New Engine:**

✨ Added `OrpheusEngine` - Real-time TTS for Orpheus-3B model with:
- multiple voice presets (`zac`, `zoe`, `tara`, etc.)
- emotive speech tags support (`<laugh>`, `<gasp>`, etc.)
- low-latency streaming (<100ms time to first audio token)
- uses an external server → lets you generate tts on another network system

**Installation:**
bash
pip install realtimetts[orpheus]

**Requires:** LM Studio (local) or compatible API server running [Orpheus-3B-0.1-ft-Q8_0-GGUF](https://huggingface.co/PkmX/orpheus-3b-0.1-ft-Q8_0-GGUF/blob/main/orpheus-3b-0.1-ft-q8_0.gguf). Load model in LM Studio before use.

**Example code:**

Here is a [code example](https://github.com/KoljaB/RealtimeTTS/blob/master/tests/orpheus_test.py) showcasing how you can use the OrpheusEngine.

- bugfix for asterisks (*) in the texts breaking synthesis with KokoroEngine (278)

- added on_word callback to TextToAudioStream that gets called when a word gets played out
Supported by AzureEngine and english voices of KokoroEngine.
An instance of class TimingInfo from BaseEngine.py gets submitted as parameter. It carries the members word, start_time and end_time. For examples please look into tests/kokoro_test.py and tests/azure_test.py

https://github.com/user-attachments/assets/e7cb35ed-2d4c-407f-a768-4f01a5afa619

- added possibility to mix voices for KokoroEngine:
python
engine.set_voice("0.714*af_nicole + 0.286*af_sky")


This feature allows you to mix a custom voice. You can use [🛠️ this tool](https://huggingface.co/spaces/ysharma/Make_Custom_Voices_With_KokoroTTS) and copy/paste the voice combination formula.

📝 [Code to test voice mixing](https://github.com/KoljaB/RealtimeTTS/blob/master/tests/kokoro_mix_voices.py) mixing voices with Kokoro