Docker-whisper: Self-hosted Whisper speech-to-text server (OpenAI API)
SMRTR summary
This Docker image provides an OpenAI-compatible Whisper speech-to-text server powered by faster-whisper. It supports all Whisper models, streaming transcription, multiple audio formats, and runs completely offline for privacy. The server offers persistent model caching, multi-architecture support, and can integrate with other AI services to build a complete self-hosted AI stack.
SMRTR provides this summary for quick context. The original article belongs to Hacker News.
Read the original article