Understand the project
Practical overview
When it fits
Use it when speech captured through a microphone needs to become cursor-inserted dictation or a transcription result that Python code can consume.
Who it is for
- People who want microphone-based speech dictation into the active cursor.
- Python developers adding microphone transcription or voice-command input to an application.
Documented uses
- Transcribe microphone speech continuously and type it at the active cursor.
- Capture a transcription result through a Python listen method for use in an application.
- Select among Whisper model sizes and English-only or multilingual variants.
Before you choose
Requirements & limits
- The README gives approximate VRAM requirements from about 1 GB for tiny and base to about 10 GB for large, with relative speed varying by model.
- English-only model variants exist for tiny, base, small and medium; the README reports their strongest performance difference for tiny and base.
- The project is Python-based, distributed as a pip package, and licensed under MIT.
Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.
Source-based practical guide
Install Whisper Mic in a Python environment
Prepare the package for command-line or Python use.
Before you start
- Python environment suitable for creating a virtual environment
- pip
Steps
Create a virtual environment.
Run the command below.
pip install whisper-mic
Expected outcome
The whisper-mic package is installed in the chosen environment.
Guide limitations
- These steps cover installation only; they do not configure a model or verify microphone access.
Source-based practical guide
Send microphone transcription to Python code
Call the documented listen method and access its returned result.
Before you start
- Whisper Mic installed in a Python environment
Steps
Import
WhisperMicfromwhisper_mic.Create an instance with
mic = WhisperMic().Call
result = mic.listen().Use or print the returned result.
Expected outcome
Python code receives a transcription result from the listen method.
Guide limitations
- The README points to cli.py for possible arguments; this recipe does not specify configuration or microphone troubleshooting.
Evidence and transparency
Sources & review
Source record details
- Source availability
- Active
- Sources checked
- 15 October 2026
- Original website title
- mallorbc/whisper_mic · Official homepage title · retained in its source language