Model · Voice and speech

Whisper

A free speech-recognition model from OpenAI that turns recordings into text in many languages and can translate speech into English text. You download and run it yourself, so it needs some technical setup.

Go to Whisper’s website

At a glance

Open or closed: Fully open
Weights and code downloadable under a standard open licence
README: code and model weights released under the MIT License.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: MIT (Permissive (e.g. Apache 2.0, MIT))
The Hugging Face card for whisper-large-v3 is tagged Apache-2.0, while the GitHub README says MIT. Both permissive.
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: Yes
Follows from the MIT licence; no separate output terms.
source · checked 12 Oct 2026 · checked on the maker's own page
Cost: Free option: Free to download; you pay for your own hardware
Plans below.
How you use it: On your own computer, Through another service
README VRAM figures are approximate (~). English-only .en versions exist for tiny to medium. Needs Python 3.8-3.11, PyTorch and ffmpeg. Weights on Hugging Face (openai org). OpenAI's paid speech API not checked.
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed: Technical
Install via pip plus ffmpeg on the command line.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: OpenAI
Repository does not state a country; no other OpenAI page could be read (fetch budget).
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
README shows no release dates; no deprecation notice found.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

What you can make with it

A voice or speech, text from a recording (main use)
A voice or speech, a written translation of a recording

audio to text

Transcribes many languages, translates speech into English text and identifies the spoken language. The turbo model is not trained for translation.

source · checked 12 Oct 2026 · checked on the maker's own page

Plans and prices

No paid plans listed.

source · checked 12 Oct 2026 · checked on the maker's own page

Where you can run it

Hugging Face

Other options for “A voice or speech, text from a recording”

Adobe Podcast (Enhance Speech), Adobe Premiere, AssemblyAI, Async (formerly Podcastle), AudioShake, Auphonic, Azure AI Speech, CAMB.AI, Cartesia, Cleanvoice AI, Clipchamp, Deepgram, Descript, Distil-Whisper, Dubverse, ElevenLabs, Filmora, Gling, Happy Scribe, Hugging Face, Kapwing, Krisp, MacWhisper, MiniMax Audio

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.