This is a submission for the AssemblyAI Challenge : Sophisticated Speech-to-Text
What I Built
Scribe
Scribe is an Obsidian (an incredible graph based note taking application) plugin that not only records your voice and transcribes it, but answers questions with "Hey Scribe", summarizes what was said, pulls out insights and graphically maps out the main points.
Repo
https://github.com/Mikodin/obsidian-scribe
Key Features
- Robust voice recorder
- Handles network failures with grace
- Has high compression for cloud storage
- Doesn't lose audio files when something goes wrong
- Can pickup from any audio file
- Voice to text raw transcription & formatting with AssemblyAI
- Summarize, get insights, and chart out what was said with ChatGPT (sorry not LeMUR - maybe coming soon)
- Clean and simple UI
Demo
Stack
Essentially the Obsidian app is the stack. It's an electron app with an extensive ecosystem.
Obsidian Dev Docs Here
I was able to leverage React along with the MediaRecorder Api.
Journey
This is something that I've wanted for quite some time. I've been trying several transcription plugins over the last year in Obsidian, but none of them do what I wanted. They were either fickle, save multi MB audio files, or were too basic.
Scribe is my attempt at solving for this.
May it be of use for you!
Thank you to dev.to, and AssemblyAI - it's an honor to submit something here.
Top comments (4)
Definitely gonna be using this! Obsidian also my main note taking app! will take advantage while my $50 credit last š
Glad to hear!!
Iām super open for feedback as well, let me know what ya think!
Another comment: the transcription is really good just as the summary, insights and the graphs are. I didn't immediately expected that the charts would be helpfull.....but they really are! I see now in less then a second the important stuff of my notes...that is really helpfull. :-)
One other remark: the popup window when you start recording is really usefull, but at t he same time it s a bit annoying because it is quite large and blocking the middle part of my screen. The best would be that it would be moveable and sizeably..would that be an option. Or move it to the upper right corner (but smaller...) I know you can start it it without the popup, but i like the popup, but smaller/less intrusive.
Hi i just starting to use your plugin. It is a nice one, but one thing I notice, the transcription is in the recorded language (dutch in my case) but the rest, summary, insights etc. is in English . Would be nice if evertything remains in the detected language of the transcription.
Keep up the good work