ros_vosk

A ROS package for speech-to-text services based on Vosk

Tutorials

sudo apt install ros-${ROS_DISTRO}-ros-vosk

don't forget to run catkin_make

If using ROS MELODIC run first:

sudo apt install python3-pip

Then run for MELODIC & NOETIC:

roscd ros_vosk
pip3 install -r requirements.txt

And if you want to use the TTS engine please run:

sudo apt install espeak
pip3 install pyttsx3

Launch the speech recognition node

roslaunch ros_vosk ros_vosk.launch

or by running:

rosrun ros_vosk vosk_node.py

Param	Description	Values	Default
models_path	path to a folder where vosk audio models are stored	string	-
use_tts_engine	use tts	True/False	False

Published topics

Topic	Type	Description
vosk/speech_recognition/vosk_result	ros_vosk/speech_recognition	a custom "speech_recognition" message
vosk/speech_recognition/final_result	std_msgs/String	a string with the final result
vosk/speech_recognition/partial_result	std_msgs/String	a string with the partial result

Subscribed topics

Topic	Type	Description
vosk/tts/status	std_msgs/Bool	the state of the tts engine. True if it is speaking False if it is not. If the status is true vosk_node won't process the audio stream so it won't listen to itself

Published topics

Topic	Type	Description
vosk/tts/status	std_msgs/Bool	the state of the engine. True if it is speaking False if it is not.

Subscribed topics

Topic	Type	Description
vosk/tts/phrase	std_msgs/String	get a string to say