The Curious AI Guy

Library / Images & audio

Whisper

Speech-to-text you can run yourself.

Replaces
LicenseMIT
GitHub stars110k
Last code update31 August 2026
SetupIntermediate about 15 minOur estimate
Paid version costs about$16.99/moOtter.ai Pro, monthly billing, 1,200 minutes a month
Per year~$203.88

New to this? What open source means and how to read this page.

What it is

An open speech recognition model that transcribes and translates audio. You run it locally, so recordings stay with you.

Good for

Transcribing interviews, meetings and videos without per-minute fees.

The catch

Accuracy varies with accent, noise and language. Larger models are slower and need a decent GPU. It gives raw text, not a finished transcript product.

Whisper versus

Whisper
PriceFreeThe software is free. You need a computer that can run it.ca. $16.99/moOtter.ai Pro, monthly billing, 1,200 minutes a month
LicenseMITCommercial license
Source codePublic, you can read and check itNot public
SetupIntermediate, about 15 minSign up and pay
Where it runsOn your own hardwareThe vendor's app or service, under their terms

The paid product's own plans and terms change. Check its site before you decide.

Install it with an AI assistant

Paste this into Claude, ChatGPT or another assistant that can work on your computer (Claude Code or Claude Desktop, for example). It is written from the project's official repository and tells the assistant to show you every command first. Setup time is our estimate: about 15 min.

I want to install and try Whisper on my own computer.

Official repository: https://github.com/openai/whisper
Official site: https://github.com/openai/whisper
License: MIT

Before you do anything:
1. Read the README and install notes in the official repository above, and nothing else. Do not follow third-party tutorials or mirrors.
2. Tell me in plain words what will be installed, what it needs (operating system, memory, graphics card, disk space, accounts) and what it will cost me, if anything.
3. Check my computer against those needs and tell me honestly if it will not work well.

This runs an AI model on my own hardware. Check my graphics card and memory first, and tell me which version or size of the model will realistically fit. Download model files only from the official page named in the README, tell me how big they are before you download, and run one small example to check it works.

Rules:
- Show me each command before you run it, and say what it does.
- Ask before anything that deletes files, changes system settings, opens a network port or needs an administrator password.
- Never put my passwords or keys on a command line, or in a file I did not choose.
- When it is installed, help me check it with one small test, and tell me how to start and stop it.
- If something goes wrong, explain it in plain words and do not guess your way around it.

Good to know before you start: Accuracy varies with accent, noise and language. Larger models are slower and need a decent GPU. It gives raw text, not a finished transcript product.

We have not run this prompt ourselves yet. Read what the assistant plans to do before you say yes.

Facts checked on 12 October 2026. We have not yet run a hands-on test of this tool. When we do, it gets a "Tested" mark here. Approximate US list prices for an individual plan, from third-party price trackers checked on 12 Oct 2026. Monthly billing where it exists. Regions, taxes and promotions change them. Confirm at the vendor before you decide.

More in Images & audio

Images & audioOpen source

Build image generation workflows as a graph of nodes.

Replaces:

Intermediateabout 20 min

saves ~$10/moDetails →
Images & audioOpen source

A free multitrack audio editor.

Replaces:

Beginnerabout 5 min

price not verifiedDetails →
Images & audioOpen source

A free RAW photo workflow.

Replaces:

Beginnerabout 5 min

saves ~$9.99/moDetails →