On Device Python Packages

bithuman

Portable C++ avatar runtime — Python bindings via pybind11. Powers the bitHuman Essence pipeline cross-platform.

pvporcupine

On-device wake word detection powered by deep learning

supertonic

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

pvkoala

On-device noise suppression 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.

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.

pvleopard

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

pvrhino

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

nanowakeword

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

pvcobra

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

violawake

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

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.

pvporcupinedemo

Porcupine wake word engine demos

picovoice

On-device voice assistant platform powered by deep learning

mozilla-voice-stt

A library for running inference on a Mozilla Voice STT model

pvrhinodemo

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

pvleoparddemo

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

picovoicedemo

On-device voice assistant platform powered by deep learning

mozilla-voice-stt-cuda

A library for running inference on a Mozilla Voice STT model

pvcobrademo

Cobra voice activity detection (VAD) engine demos.

dictate-mlx

65ms voice-to-text on Apple's Neural Engine. Push-to-talk dictation for macOS — 100% local, free, open source.

pvfalcon

Falcon Speaker Diarization Engine

ppnrespeakerdemo

⚠️ DEPRECATED: This package is no longer maintained.