[going to be] an open source audio- and videotranscription software
Note:
Currently, transcribee is heavily work-in-progress and not yet ready for production use. Please come back in a few weeks / months.
transcribee 🐝 aims to make the workflow for media transcription easier, faster and more accessible.
- It can automatically generate a draft transcript of your audio
- It allows you to quickly improve the automatic draft and fix any errors
- It's collaborative – split the work with your friends or colleagues
- It's open-source
To get started with developing or to try the current state of transcribee, follow the instructions in the development setup document.
Note:
We're heavily working on transcribee. Not all steps described here are already implemented.
Creating a transcript with transcribee 🐝 is done with the following steps:
-
Import your media file
During import, your audio file is automatically converted to text using state-of-the-art models1. transcribee 🐝 also automatically detects different speakers in your file.
-
Manually improve the transcript
After the automatic transcript is created, you can edit it to correct any mistakes the automatic transcription made.2 You can also name the speakers.
Since transcribee 🐝 is a collaborative software, you can do this step (and all other manual steps) together with others. All changes are instantly synced with everyone working on the transcript.
-
Automatic re-alignment
To make sure that the timestamps of your corrected text are still correct, transcribee 🐝 matches this text back up with the audio.
-
Manual re-alignment
Now you can check the automatically generated timestamps and correct them.
-
Export
Once you are happy with the transcript, you can export it.
- Funded from March 2023 until September 2023 by
