github.com
Auralis
A text-to-speech inference engine with support for voice cloning.
https://github.com/astramind-ai/AuralisAbout This Resource
A text-to-speech inference engine with support for voice cloning. It provides serving and processing tools for generating speech from text with supported models.
Saved Notes
Original notes saved with this link. They may describe an earlier version.
GitHub - astramind-ai/Auralis: A Fast TTS Engine
Overview
Transform text into natural speech (with voice cloning) at warp speed. Process an entire novel in minutes, not hours.
What is Auralis? 🚀
Auralis is a text-to-speech engine that makes voice generation practical for real-world use:
Key Features
- Ultra-fast processing: Convert the entire first Harry Potter book to speech in 10 minutes (realtime factor of ≈ 0.02x!)
- Smart audio enhancement: Automatically improve reference audio quality, even from low-quality microphone recordings
- Resource-efficient: Configurable memory footprint through scheduler_max_concurrency
- Concurrent processing: Handle multiple requests simultaneously
- Streaming capability: Process long texts incrementally