v0.4.54

KoljaB/RealtimeTTSv0.4.54Mar 22, 2025by KoljaB

AI Summary

A new OrpheusEngine is added to support the Orpheus-3B model, featuring emotive speech tags and low-latency streaming capabilities.

Key Highlights

Added `OrpheusEngine` for real-time TTS
Multiple voice presets and emotive speech tags support
Low-latency streaming (<100ms time to first audio token)
External server integration for network generation

New Features

OrpheusEngine
Emotive speech tags
Low-latency streaming

Full Release Notes

# RealtimeTTS v0.4.54 Release Notes

**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.