← Discover
GitHub · openai/whisper↑ +150 today

Transcribe sounds with artificial intelligence

Developed by OpenAI, Whisper is a speech recognition model trained by large-scale weak supervision learning method. It offers high accuracy rates in converting and translating multilingual audio data into text.

Updates

  • November 3, 2026: Stars 106,452 → 111,832, latest release v20250625 (June 26, 2025).
  • August 2, 2026: Stars 101,952 → 106,452, latest release v20250625 (June 26, 2025).

What you get

  • Convert audio files to text with high accuracy.
  • Translating conversations from different languages ​​into English.
  • Language identification and speech activity detection in audio content.

Installation

Install FFmpeg
sudo apt update && sudo apt install ffmpeg
Install Python dependencies
pip install setuptools-rust
Install Whisper
pip install openai-whisper

Running it

Convert audio file
whisper audio.flac --model turbo

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to convert my audio file into text using the Whisper tool. I made the necessary installations on my system. What is the basic command structure I need to type in the terminal to translate the content of my audio file into text, and how should I use the language specification parameter for audio files in different languages?

Repository: https://github.com/openai/whisper. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

WhisperArtificial Intelligence
Who it is forFor developers and researchers who want to automate the process of converting audio data to text, performing translations, or language identification.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-07: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.