/ Models

Whisper Large v3 Turbo (whisper.cpp)

OpenAI · local · Transcription · local/whisper-large-v3-turbo

Transcription on your Mac timestamps offline MIT

99 languages, fully offline, free. The fallback that always works — 1.6 GB and ≥16 GB RAM.

Install on 00

Get the 00 app

Free · macOS

Your agents, your models, your machine — this model installs with one click once the app is on board.

Download free →

What it costs

Per minute of audio
free
Quoted as
nothing per minute — it runs on hardware you own
Runs
on your own machine

Free to run: it downloads once and works on the machine you already own. It costs you disk, memory and battery instead.

How it performs

Word errors
7.4%
Latency
Speed
146× real time
Languages
99
Streaming
Speaker labels
Timestamps
yes
Voice cloning
Licence
MIT

A blank cell means the row does not state it, not that the answer is no. Word-error rates come from one independent harness, so they compare with each other only.

Using it

Runs on your own machine. It downloads once and then works offline: no key, no account, no per-minute cost.

These are not AI-token prices, and these engines do not answer at the hosted endpoints — 00 speaks to them from your machine, with your credentials. The speech models that do run on AI tokens are one click away on the media page.

Pick it per agent in the app. Get 00.

← every speech model