Plugin: Audio Transcriber

Plugins
1

Joplin Audio Transcriber Plugin v1.0.0 Released

Hi everyone,

A few days ago I started a discussion about bringing audio transcription directly into Joplin. Today I’m happy to announce that v1.0.0 of the Joplin Audio Transcription Plugin is now available.

Repository:

What This Plugin Does

The plugin allows you to:

  • Select an audio file
  • Transcribe it directly inside Joplin
  • Insert the transcription into your note

No more switching between Joplin and external transcription tools.

Demo video: YouTube

Why I built this

I use Joplin mainly for jotting down meeting notes. My current workflow is as follows.

  1. I go to a meeting. I make quick notes and I turn on a voice recorder.
  2. After the meeting I put the audio file in an audio transcriber (I've been using turboscribe).
  3. The transcriber returns a big piece of text with timestamps and distinction between people.
  4. I paste the text and my notes in joplin along with my note template and tell the LLM plugin it to put it into the template.
  5. I fact check it.

This process worked, but the part of uploading the audio file to the transcriber feels cumbersome. Since I just want to record the audio and paste it into my Joplin notes with the transcribed audio under it I don't want to go to an external application and upload it there to get the transcription.

Key Features (v1.0.0)

  • :studio_microphone: Audio Transcription - Transcribe attached audio files directly from your Joplin notes
  • :robot: Multiple AI Providers - Support for OpenAI Whisper and Google Gemini transcription APIs
  • :gear: Customizable Settings:
    • Select from multiple transcription providers
    • Configure API keys securely
    • Optional: specify a custom model
    • Optional: set language for transcription
    • Optional: add custom instructions via prompt
  • :wrench: Extensible Architecture - Easy to add new transcription providers
  • :memo: Seamless Integration - Transcribed text is appended directly to your notes

Intended Use Case

This plugin is especially useful if you:

  • Record meetings or lectures
  • Store audio files in Joplin
  • Use transcripts for:
    • Searchability
    • Summarization with LLM plugins
    • Structured documentation
    • Archiving conversations

Feedback Welcome

This is the first stable release (v1.0.0), and I’d appreciate feedback on:

  • Performance
  • Accuracy
  • Language support
  • UX improvements
  • Feature ideas

If you'd like to contribute or open an issue, feel free to do so on GitHub.

What’s Next

Some ideas for future versions:

  • Speaker distinction improvements
  • Better progress feedback
  • More language optimizations
  • Deeper integration possibilities
  • ~~ More plans can be found in the GitHub issues ~~

Discussion topics

I'm curious if other people have a similar workflow.

  • Do you use AI to transcribe recordings of your meetings?
  • Or if not, do you think this plugin will get you started with AI audio transcription?
4 Likes
2

That's great, thanks for sharing this! I think some support for local AI would make sense here since transcribing audio doesn't require too much power. Maybe support for any generic MCP server would be enough?

1 Like
3

Yeah for sure. I'll add it to the issues. APIs were easier to implement for me right now, but local models would be a good addition.

2 Likes
4

This is awesome. I am very interested in this plugin but would want it to be able to run locally so I am happy to see that has already been requested. Som other features that would be great is being able to process in bulk somehow, maybe having joplin watch a folder and subfolders where audio recordings are.
I have had mixed results with Diarization/speech recognition where sometimes it does not work. I often wonder if there is a way to create a speaker profile that is saved, so where that voice heard, the name is automatically applied.

1 Like
5

So what happened to this idea?