🎧 Meeting Room
Recording in, minutes out — then question the transcript.
🎙️ Transcription uses FAL Whisper and the summary uses OpenAI. The follow-up questions run on a local Ollama model, so they cost nothing.
The actual app, as it opens in NodeTool — built with the visual App Builder, no code.
What you put in
- audioMeeting recording
- textYour question
- choiceAnswer tone
What you get out
- TextTranscript
- TextMeeting notes
- Structured dataAction items
- TextTranscript used
- TextAnswer
How it works
- Step 1
Fill in a few fields
Plain-language inputs — meeting recording, your question, answer tone. No settings, no jargon.
- Step 2
Click “Transcribe”
The workflow runs behind the scenes — on your machine or with your own provider keys. You pay providers directly, or run local models for free.
- Step 3
Watch results stream in
Results appear live in the app: transcript, meeting notes, action items, transcript used.
It's an app until you want more
Every screen in this app runs a real NodeTool workflow. Open any of them on the canvas to swap models, change prompts, or add steps — then publish your remix as a new app for your team.
More mini apps
Ask your own documents — with a local mode that never leaves your machine.
Generate a gallery, pick one, polish it.
Brief → direction → storyboard → cut → key art.
One brief, three frontier models, answered side by side.
Drag five sliders and watch the photo re-render — then run the same grade over a whole folder.
A deck of flashcards and the concept behind it, side by side.