This major update brings comprehensive multilingual support to Orpheus-FASTAPI:
• Added 16 new voice actors across 7 languages (French, German, Korean, Hindi, Mandarin, Spanish, Italian)
• Released 6 language-specific optimized models for superior pronunciation and fluency
• Enhanced UI with dynamic language selector and voice filtering
• Updated Docker Compose workflow to simplify language-specific model deployment
• Reorganized code architecture with language-aware voice mappings
All voices support the same emotion tags and audio quality features as the original English voices, maintaining compatibility with existing applications while expanding international usability.
- Added optional Docker Compose setup integrating Orpheus-FastAPI and a GPU-enabled llama.cpp inference server.
- Includes automatic model download via model-init service.
- Native install path remains unchanged to ensure compatibility for non-Docker users.
- Updated README to include contribution credit for @richardr1126 (https://github.com/richardr1126).
- Squash-merged PR #21 with clean commit history.
Thank you to @richardr1126 for the Docker orchestration work and for helping expand accessibility for container-based deployments!
README.md:
- Added new quants (Q2_K, Q4_K_M)
TTS_ENGINE:
- Updated the External Inference Server section:
- Made the model parameter configurable via ORPHEUS_MODEL_NAME environment variable
Environment:
- Updated .env.example to include this new parameter
