Alvoff Inference provides cheap and reliable API for speech-to-text, text-to-speech based out of India. We aim to be the one stop solution for voice related inference. Our infrastructure is purpose-built for audio workloads, which means low latency and lower cost compared to general-purpose cloud providers. You can signup on the platform and get $5 of inference for free.
A lightweight Docker image that provides a single HTTP proxy endpoint backed by many Tor exit IPs, designed for web crawling and scraping.
A single Tor process handles all circuits using SOCKS5 authentication-based isolation (IsolateSOCKSAuth). A Go-based HTTP proxy sits in front, round-robin routing each request through a different circuit credential - no HAProxy, no Privoxy, no per-instance processes.
Every container runtime on macOS runs a Linux VM. Linux doesn't have Metal support, so you can't use MLX, MPS, or other Metal-accelerated frameworks inside a container.
MetalBox solves this by running workloads as native macOS processes with Docker-like resource management:
* Hard memory limits (RSS watchdog that kills and restarts processes when limits are exceeded)
* Metal/MLX GPU memory caps (automatically injected via a wrapper)
* Filesystem and network sandboxing using macOS sandbox-exec
