A lightweight client for running Orpheus TTS locally using LM Studio API over WebRTC with FastRTC.
- 🎧 High-quality Text-to-Speech using the Orpheus TTS model
- 💻 Completely local - no cloud API keys needed
- 🔊 Streaming audio over WebRTC with FastRTC
- 💬 ChatUI for displaying conversation history + downloading audio
- 🔊 Multiple voice options (tara, leah, jess, leo, dan, mia, zac, zoe)
- Install LM Studio
- Download the Orpheus TTS model (orpheus-3b-0.1-ft-q4_k_m.gguf) in LM Studio
- Load the Orpheus model in LM Studio
- Start the local server in LM Studio (default: http://127.0.0.1:1234)
- Install dependencies:
python3 -m venv venv source venv/bin/activate pip install -r requirements.txt - Run the script:
python streaming_text_to_speech.py
python gguf_orpheus.py --text "Your text here" --voice tara --output "output.wav"
Apache 2.0