A

audio-processing

Self-hosted speech server in one Docker image. OpenAI-compatible /v1/audio/transcriptions and /v1/audio/speech across 12 ASR models (Whisper, Parakeet, Canary, Sherpa-ONNX, Vosk) and 3 TTS engines (Kokoro, Qwen3-TTS voice cloning, Chatterbox Turbo). Live WebSocket ASR, file staging, MCP built in. CPU + CUDA images.

[2025] Raspberry Pi control system for interactive art installations. Orchestrates LED lighting, FM radio, live audio mixing, and environmental monitoring through unified Flask interface with 24/7 exhibition reliability and automatic service management.