More information about this video.
Skills used:
- GitHub - OpenVoiceOS/skill-ovos-date-time: Mycroft AI official Date and Time Skill, providing the current time, date and day of week for cities around the world.
- GitHub - OpenVoiceOS/skill-ovos-personal: OpenVoiceOS official Personality Skill - answers basic personality questions around OVOS
- GitHub - OpenVoiceOS/ovos-skill-ddg: duck duck go skill
- GitHub - OpenVoiceOS/ovos-skill-wolfie: wolfram alpha spoken answers skill
- GitHub - OpenVoiceOS/ovos-skill-pyradios: Pyradios skill for OpenVoiceOS
- GitHub - OpenVoiceOS/ovos-skill-wordnet: wordnet skill
- GitHub - OpenVoiceOS/skill-ovos-fallback-chatgpt
- GitHub - OpenVoiceOS/ovos-skill-icanhazdadjokes: i can haz dad joke skill
The fallback ChatGPT skill interacts with a local AI as demonstrated in this video.
Here is the fastfetch for the laptop specs (hardware and software).
Below is the Waybar module I wrote which interacts with Open Voice OS bus.
#!/bin/env bash
#
# This module listens to the Open Voice OS message bus and display
# a JSON object based on the message type. This JSON object has to
# be compatible with the expected output by Waybar.
# websocat and jq must be installed before running the script.
#
# Documentation: https://openvoiceos.github.io/message_spec/
# Variables
sleep_utterance=1
sleep_speak=3
main_unicode="✨"
websocket_url="ws://127.0.0.1:8181"
# Kill websocat if already running
if pgrep websocat &>/dev/null; then
killall websocat
fi
# Initial printed message
printf '{"text": "%s Open Voice OS"}\n' "$main_unicode"
# Connection to the bus via websocat
websocat -t - -U autoreconnect:"$websocket_url" | while read -r line; do
# JSON parsing
message_type="$(echo "$line" | jq -r .type)"
message_utterance="$(echo "$line" | jq -r '. | select(.type=="'"$message_type"'") | .data.utterance')"
message_utterances="$(echo "$line" | jq -r '. | select(.type=="'"$message_type"'") | .data.utterances[0]')"
# Check for specific messages
case "$message_type" in
recognizer_loop:wakeword)
printf '{"text": "%s Open Voice OS", "class": "listen"}\n' "$main_unicode"
;;
recognizer_loop:record_end)
printf '{"text": "%s Open Voice OS"}\n' "$main_unicode"
;;
recognizer_loop:utterance)
printf '{"text": "⭐ %s"}\n' "${message_utterances^}"
sleep "$sleep_utterance"
;;
speak)
printf '{"text": "💫 %s"}\n' "${message_utterance^}"
sleep "$sleep_speak"
;;
recognizer_loop:audio_output_end)
printf '{"text": "%s Open Voice OS"}\n' "$main_unicode"
;;
esac
done