On Device Python Packages

pvporcupine

On-device wake word detection powered by deep learning

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.

supertonic

Lightning-Fast, On-Device TTS — running natively via ONNX.

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.

pvkoala

On-device noise suppression powered by deep learning

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.

omi-med-stt

On-device English medical speech-to-text — CLI for Omi Med STT v1 (MLX / NeMo / parakeet.cpp)

yazses

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

nanowakeword

A lightweight, wake word detection engine. Train custom, high-accuracy models with minimal effort.

youty-mcp

Turn YouTube, Instagram, and TikTok videos into a local, AI-readable knowledge base — 100% on-device. macOS app + CLI + MCP server.

pvleopard

On-device speech-to-text engine powered by deep learning

pvrhino

On-device Speech-to-Intent engine powered by deep learning

faro-embedded-search

Incremental hybrid retrieval (lexical + vector, RRF-fused) with identical ranking on server Postgres and on-device SQLite

pvcobra

On-device voice activity detection (VAD) powered by deep learning

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.

bithuman-mcp

Public mirror of the bitHuman SDK — pip install bithuman. Generated/published from the private bithuman-sdk-internal monorepo. [public]

apii

Keep Arabic & Gulf personal data off the LLM — local-first, reversible PII tokenization (CLI, proxy, and a Claude Code hook).

mozilla-voice-stt-cuda

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.

violawake

Open-source wake word SDK — production TemporalCNN model, 8-phase training pipeline, ONNX inference, Python-first. The open alternative to Porcupine.

picovoice

On-device voice assistant platform powered by deep learning

dictate-mlx

Push-to-talk voice dictation for macOS. 100% local, free, open source. Apple Silicon MLX. No cloud, no subscription.

picovoicedemo

On-device voice assistant platform powered by deep learning

gigastt

Local STT server powered by GigaAM v3.