petewarden/spchcat
A local speech-to-text command-line tool for Linux and Raspberry Pi that transcribes audio from files or microphone without network access.
Not currently ranked — collecting fresh signals.
star history
spchcat uses Coqui’s speech-to-text models and TensorFlow to run speech recognition entirely offline on the user’s machine. It reads audio input from WAV files, microphones, or system audio sources and outputs text transcripts. The tool relies on KenLM for language modeling and models trained on Mozilla’s Common Voice dataset, supporting multiple languages through Coqui’s model library.
Frequently asked
- What is petewarden/spchcat?
- A local speech-to-text command-line tool for Linux and Raspberry Pi that transcribes audio from files or microphone without network access.
- Is spchcat open source?
- Yes — petewarden/spchcat is open source, released under the MPL-2.0 license.
- What language is spchcat written in?
- petewarden/spchcat is primarily written in C.
- How popular is spchcat?
- petewarden/spchcat has 486 stars on GitHub.
- Where can I find spchcat?
- petewarden/spchcat is on GitHub at https://github.com/petewarden/spchcat.