In simple English
This tool listens to audio recordings and writes down what people say. It handles many different languages and can even translate foreign speech into English text. You run it on your own computer so your audio files stay private. It costs nothing to download and use under an MIT licence. You do need a computer with enough memory and processing power to run it smoothly.
What it is
Whisper is an open-source speech recognition system built by OpenAI. It uses a neural network (a computer system inspired by the human brain that learns to find patterns in data) to transcribe audio with high accuracy.
What it is good for
Solo builders who need to add subtitles to videos, transcribe customer interviews, or build voice-controlled apps without paying for a commercial cloud service.
- Transcribes audio in dozens of different languages with high accuracy.
- Runs entirely on your own machine so your data stays private.
- Provides both a simple command-line tool and a Python library for developers.
- Requires 1 GB to 10 GB of memory depending on the model size you choose.
- Needs the FFmpeg command-line tool installed separately on your system.
- Processing long audio files can take significant time on standard computer processors.
Paid cloud transcription services like Otter or manual typing
FFmpeg for audio file conversion and preparation
- SYSTRAN/faster-whisper26k stars
Runs the same speech recognition models much faster and using less memory.
- openai/openai-python32k stars
Lets you call the official hosted transcription API instead of running models locally.
- snapcast/snapcast8.0k stars
A server and clients that play one audio stream in several rooms, kept in time with each other.
- MusicPlayerDaemon/MPD2.8k stars
A background music player with no interface of its own, controlled over a network by separate client programs.
- AcademySoftwareFoundation/OpenTimelineIO2.0k stars
An interchange format and library for editing timelines: the order and length of cuts, and references to the media, but not the media.
pip install -U openai-whisper pip install setuptools-rust