jarvis

(★ 28)

A minimalist local voice assistant built in C++ using Whisper.cpp, llama.cpp, and Piper TTS.

Owner Repos

sarah ★ 9

A fully offline JARVIS-inspired voice assistant written in C++.

C++

File Explorer

ZIP Download
  • buildMe.sh
  • LICENSE
  • README.md
  • setup.sh
  • testMe.sh

# Use via CDN

jsDelivr

jsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.

Link
Example

Command Glossary

Commands referenced in this DOCs, explained below.

🔍

piper-tts

View Details ▼

This command is an alias of `piper`.

tldr piper

View documentation for the original command:

🔍

piper

View Details ▼

A fast, local neural text to speech system.
Try out and download speech models from <https://rhasspy.github.io/piper-samples>.

echo {{Thing to say}} | piper -m {{path/to/model.onnx}} -f {{outputfile.wav}}

Output a WAV [f]ile using a text-to-speech [m]odel (assuming a configuration file at model_path + `.json`):

echo {{Thing to say}} | piper -m {{path/to/model.onnx}} -c {{path/to/model.onnx.json}} -f {{outputfile.wav}}

Output a WAV [f]ile using a [m]odel and specifying its JSON [c]onfig file:

echo {{Warum?}} | piper -m {{de_DE-thorsten_emotional-medium.onnx}} --speaker {{1}} -f {{angry.wav}}

Select a particular speaker in a voice with multiple speakers by specifying the speaker's ID number:

// repository documentation