Offline Asr Python Packages

ffvoice

Offline speech-to-text & speaker diarization for AI agents — Whisper ASR + MCP server + CLI + Python bindings, fully on-device, no cloud | 离线语音识别与说话人分离,Agent 开箱即用

gigaam-multilingual-mlx

Offline speech-to-text for Russian, Kazakh, Kyrgyz & Uzbek on Apple Silicon — native MLX, quantized GigaAM, CLI and OpenAI-compatible local server.

microasr

Lightweight real-time ASR powered by a Microsoft offline speech recognition model. CPU-only, supporting 10 languages, Windows, Linux, macOS, and C#, C++, Python SDKs. 基于微软离线语音识别模型的轻量级实时 ASR，纯 CPU 运行，支持 10 种语言及 Windows、Linux、macOS，提供 C#、C++ 和 Python SDK。