OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

WhisperWriter

WhisperWriter is a Python desktop dictation app that records microphone speech, transcribes it with Whisper, and writes the result into the active window. It offers continuous, voice-activity-detection, press-to-toggle and hold-to-record modes, with transcription through a local faster-whisper model or a configured API endpoint.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

WhisperWriter — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want microphone dictation to appear directly in the active window and need to choose recording behavior or a local-versus-API transcription route.

Who it is for

  • People who want to dictate text directly into the desktop window they are using.
  • Python users setting up a configurable speech-to-text utility with local-model or API transcription.

Documented uses

  • Dictate text into the active desktop window using a keyboard shortcut.
  • Keep capturing speech across pauses with continuous recording, or choose a mode that waits for renewed input.
  • Choose local faster-whisper transcription or configure OpenAI API or another base URL endpoint.
Before you choose

Requirements & limits

  • The default transcription route is local through faster-whisper; API use is configurable, and non-local OpenAI API use requires an API key.
  • Four recording modes differ in how pauses and keyboard input start or stop recording.
  • The project documents Python 3.11, Git and dependency installation as setup requirements.
  • GPU execution with faster-whisper requires cuBLAS for CUDA 12 and cuDNN 8; the configuration also offers CPU and automatic device selection.
  • The repository lists the project under the GPL-3.0 license.

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

Set up WhisperWriter for desktop dictation

Install the Python app, configure it, and start its keyboard listener for dictation into the active window.

Before you start

  • Git
  • Python 3.11
  • For local GPU transcription: NVIDIA cuBLAS for CUDA 12 and cuDNN 8

Steps

  1. Clone the repository and enter its directory: the command below then cd whisper-writer.

    Documented command
    git clone https://github.com/savbell/whisper-writer

  2. Create and activate a virtual environment using the documented commands for your operating system.

  3. Install dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  4. Run the command below; configure and save settings when the Settings window appears, then press Start.

    Documented command
    python run.py

  5. Press the activation shortcut (Ctrl+Shift+Space by default) to record and transcribe into the active window.

Expected outcome

WhisperWriter listens for its activation shortcut and inserts completed transcriptions into the active window.

Guide limitations

  • The setup instructions require Python 3.11.
  • GPU use with faster-whisper requires the specified NVIDIA libraries; CPU is available as a local-model device option.
  • Using the OpenAI API requires an API key for non-local API use.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
savbell/whisper-writer · Official homepage title · retained in its source language
How we review sourcesSuggest a correction