Offline Python Packages

vosk

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

deepspeech

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

libzim

Libzim binding for Python: read/write ZIM files in Python

castlabs-evs

Castlabs Electron for Content Security

deepspeech-gpu

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

deepspeech-tflite

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

pytest-local-badge

Generate self-hosted SVG pytest status and coverage badges. No third-party shield service required.

memorised-them-all

Give any AI assistant a private, token-free memory of your files — Claude, Gemini, Cursor, VS Code, Windsurf, Codex & Grok. Converts attachments (PDF/Office/EPUB/archives) to Markdown and builds a searchable knowledge-graph memory to recall from. 100% local, deterministic, model-free (no LLM/GPU). Incremental & portable; English + Bengali. MIT.

aura-memory

Cognitive memory for AI agents. Pure Rust, <1ms recall, 2.7MB, zero cloud. Patent Pending.

whispergram

Local, offline transcriber for Telegram & Instagram chat exports — voice/video notes via Whisper (faster-whisper), screenshots via OCR, photos/stickers/GIFs via a local vision model. Interactive menu or CLI; merges everything into one chronological, LLM-ready Markdown file. No cloud, no API key.

caliper-ai

See what your AI coding cost and produced, from the logs already on your disk. Offline, no account.

resolvekit

Entity and place resolution system that maps messy place/entity strings and codes to canonical entities

yazses

Local, offline voice dictation for Linux, macOS, and Windows — hold a key, speak, release

ansede-static

Offline SAST that detects IDOR, missing authentication, and ownership bypass. OWASP recall 62%, CVE recall 96.3% across 5 languages. Beats Semgrep OSS on recall.

twzrd-receipt-verifier

Standalone offline verifier for TWZRD receipts: AO-Receipt V5/V6 (keccak256 leaf) and genesis cNFT receipts (Ed25519 over compact JSON). No trust in TWZRD servers or code.

prompt-armor

Open-source prompt injection detector — 5 layers, 91.7% F1, ~27ms, offline, Apache 2.0

card-generator

Python library to generate and validate credit card numbers. Features a fast, offline BIN lookup using a local database. Zero dependencies, no API keys needed. Perfect for generating test data.

whisper-python

Whisper Python Untuk mendapatkan teks dari sebuah audio kini tidak perlu convert manual tidak perlu FFMPEG!

whisper-local

Free, open-source, 100% offline AI dictation for Windows & macOS. Wispr Flow / Dragon alternative. Push-to-talk hotkey, voice commands, transforms, sub-second latency. Powered by Whisper. No cloud, no subscription, no telemetry.

whisperpipe

A resource-efficient streaming architecture for OpenAI Whisper. Real-time, offline and local speech-to-text transcription.

mozilla-voice-stt-tflite

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

mozilla-voice-stt

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

voxpulse

A lightweight CNN-based framework to train custom wake words offline. Features automated data augmentation, dynamic pathing, and RMS silence gating

apotrope

Offline, single-executable Windows security posture auditor. 50+ CIS-mapped checks, a 0–100 score, and a self-contained HTML report. No cloud, no agent. MIT.