Skip to content

Releases: Lex-au/Orpheus-FastAPI

Orpheus-FASTAPI v1.1

22 Mar 23:02
@Lex-au Lex-au
v1.1
db0ac92

Choose a tag to compare

View all tags
Orpheus-FASTAPI v1.1 Latest
Latest

🎙️ Orpheus v1.1.0 — FastAPI TTS Server with Web UI & OpenAI-Compatible API

✨ What’s New

  • 🧵 Long-form audio support with intelligent sentence batching + crossfade stitching
  • 🔊 Improved audio quality via smarter token buffer alignment
  • ⚙️ .env support for cleaner configuration (editable via the Web UI)
  • 🖥️ Hardware auto-detection for GPU/CPU and adaptive optimisation
  • 📊 Detailed performance reporting for audio generation

⚡ Quick Start

git clone https://github.com/Lex-au/Orpheus-FastAPI.git
cd Orpheus-FastAPI

# Create virtual environment
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

# Install PyTorch with CUDA support (adjust for your CUDA version)
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124

# Install dependencies
pip install -r requirements.txt

# Start the server
python app.py
Assets 2
Loading

Orpheus-FASTAPI v1.0

22 Mar 18:46
@Lex-au Lex-au
v1.0
b56472c

Choose a tag to compare

View all tags
Orpheus-FASTAPI v1.0

🎙️ Orpheus v1.0.0 — FastAPI TTS Server with Web UI & OpenAI-Compatible API

Orpheus is a high-performance, GPU-optimised Text-to-Speech (TTS) server built with FastAPI.
This first stable release features a modern web interface, OpenAI-style API compatibility, and support for 8 unique voices with emotional tags — all tuned for RTX GPUs.

🔧 Features

  • 🔗 OpenAI /v1/audio/speech compatible
  • 🌐 Clean Web UI with waveform visualisation
  • 🎧 8 distinct voices (male + female)
  • 🎭 Emotion tags: <laugh>, <sigh>, <gasp>, etc.
  • ⚡ GPU-accelerated (parallel CUDA, memory-optimised)
  • 🧠 Connects to local LLM inference servers (e.g., GPUStack, LM Studio)

📦 Quick Start

git clone https://github.com/Lex-au/Orpheus-FastAPI.git
cd Orpheus-FastAPI
python -m venv venv && source venv/bin/activate
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu124
pip install -r requirements.txt
uvicorn app:app --host 0.0.0.0 --port 5005 --reload
Loading