mgonzs13/whisper_ros

Speech-to-Text based on SileroVAD + whisper.cpp (GGML Whisper) for ROS 2

54
/ 100
Established

This project helps roboticists and engineers enable their robots to understand spoken commands and transcribe audio in real-time. It takes live audio input from a robot's microphone, processes it to detect when someone is speaking, and then converts the speech into text. The output is a stream of transcribed text that the robot can then use for interaction or task execution.

Use this if you are developing ROS 2-based robots that need to interpret human speech and respond to voice commands in real-time.

Not ideal if you need to analyze pre-recorded audio files or if your robotic system does not use the ROS 2 framework.

robotics voice control speech recognition human-robot interaction robot programming
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

91

Forks

21

Language

C++

License

MIT

Last pushed

Mar 06, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/mgonzs13/whisper_ros"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.