HN Showcase
Back to browse
GitHub Repository

Docker image for a self-hosted Whisper speech-to-text server with speaker diarization and OpenAI-compatible transcription and translation APIs. Powered by faster-whisper. Supports all Whisper models, NVIDIA GPU (CUDA) acceleration, JSON/SRT/VTT output, SSE streaming, offline mode, and multi-arch (amd64, arm64).

57 starsPython

Docker-whisper: Self-hosted Whisper speech-to-text server (OpenAI API)

by hwdsl2·Apr 11, 2026·6 points·1 comment
Visit ProjectView on HN

AI Analysis

●●SolidCozySolve My Problem

One-command Docker deploy from hwdsl2, who maintains trusted WireGuard and OpenVPN images.

Strengths
  • •hwdsl2's track record with security-focused Docker images (WireGuard, IPsec VPN) signals long-term maintenance
  • •Multi-arch builds (amd64/arm64) means it runs on Raspberry Pi and cloud instances without recompilation
  • •WHISPER_LOCAL_ONLY mode enables true air-gapped deployment with pre-cached models
Weaknesses
  • •No built-in authentication — you must handle API security via reverse proxy or network isolation
  • •OpenAI-compatible Whisper wrappers already exist; faster-whisper backend isn't unique
Target Audience

Developers wanting private, self-hosted transcription without OpenAI API calls

Similar To

faster-whisper · whisper-docker · localai

Similar Projects

AI/ML●Mid

Docker AI Stack – Deploy 8 self-hosted AI services with one command

Yet another one-command AI stack when Ollama and Jan already exist.

Ship It
hwdsl2
101mo ago