Practical overview
When it fits
Use Spchcat for local, command-line transcription when your input is a WAV file, microphone audio or system audio and terminal text is suitable.
Who it is for
- Linux users who want terminal-based transcription of WAV recordings.
- Raspberry Pi users setting up local speech recognition.
- People who want to transcribe speech from a microphone or audio playing on their computer.
Documented uses
- Turn WAV recordings into text in the terminal.
- Capture microphone speech for simple note-taking.
- Transcribe speech contained in system audio, including audio from videos or songs.
- Select a supported language model for transcription.
Requirements & limits
The project is open source under the MPL-2.0 license. Documentation describes Debian package installation for Debian-based x86 Linux and Raspberry Pi.
- The tool runs locally and the README states that it makes no web API calls or network activity.
- The documented x86 package targets Debian-based systems and requires PulseAudio; other distributions are listed as unsupported.
- The Raspberry Pi instructions report testing on a Raspberry Pi 4 with a specific Raspbian release and expect failure on Raspberry Pi 1 and 0.
- Recognition accuracy varies by language and by audio conditions, accent and vocabulary complexity.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Transcribe a WAV file from the terminal
Use Spchcat to convert one WAV file or a folder of WAV files into terminal text.
Before you start
- Spchcat installed on a supported Debian-based x86 Linux system or Raspberry Pi.
- PulseAudio is required for the documented x86 installation.
- A WAV file; FFmpeg is suggested by the project for converting other formats.
Steps
Install Spchcat using the package documented for the relevant platform.
Pass a WAV filename to Spchcat, for example: spchcat audio/8455-210777-0068.wav.
To process a folder, provide its path; the tool transcribes WAV files within it.
Expected outcome
Recognized speech is output as text in the terminal.
Guide limitations
- Other x86 Linux distributions are listed as unsupported.
- Accuracy varies with language, training data, noise, accent and word complexity.
Capture and transcribe microphone or system audio
Display recognized speech from the default microphone or audio playing on the computer.
Before you start
- Spchcat installed on a documented Linux or Raspberry Pi setup.
- A microphone for microphone capture, or system audio to transcribe.
Steps
Run spchcat without arguments to capture from the default microphone.
Speak into the microphone; recognized words appear in the terminal.
For audio playing through another program, run spchcat --source=system.
Expected outcome
Spchcat attempts to recognize speech and display it in the terminal.
Guide limitations
- Recognition is described as a work in progress and depends on noise, accent and word complexity.
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 15 October 2026
- Original website title
- petewarden/spchcat · Official homepage title · retained in its source language