Skip to main content
The Audio app is a voice-to-notes workflow. Users can record or upload audio, get a transcript, then generate a structured summary with action items. It is a much more useful demo than a plain “speech-to-text only” page.

​
What Users Can Do

The current app is built around a simple but practical workflow:
  1. record audio or upload a file
  2. transcribe it
  3. generate a summary
  4. review action items
  5. revisit previous recordings later
This is a strong pattern for meeting notes, voice memos, interviews, and internal productivity tools.

​
What Powers It

The app currently uses:
  • Replicate Whisper for transcription
  • OpenAI via the AI SDK for structured summaries
  • storage for uploaded audio files
  • Supabase for recordings, transcripts, and summaries
That means the old description “Whisper only” is too narrow. The product is really a small voice workflow app with storage, history, and AI post-processing.

​
What You Need

To run this app, set up Supabase, OpenAI, Replicate, and Storage.

Supabase

Needed for auth, saved recordings, transcripts, and summaries.

Storage

Needed for uploaded recordings.

OpenAI

Needed for the structured summary step.

Replicate

Needed for the current Whisper transcription path.

​
How It Works

Here is the real flow in simple language:
  1. the user records audio in the app or uploads a file
  2. the file is saved to object storage
  3. Replicate Whisper creates a transcript
  4. the transcript is saved in Supabase
  5. OpenAI generates a structured summary, title, and action items
  6. the user can reopen that recording later and review everything
This is why the app is useful. It is not just transcription. It turns raw audio into something easier to act on.

​
Why This App Is Useful As A Template

You can repurpose the same pattern for:
  • meeting summarizers
  • founder voice memo tools
  • podcast notes
  • sales call summaries
  • interview analysis
  • private internal knowledge capture

​
Files To Know

If you want to customize this app, start here:
  • app/(apps)/audio/toolConfig.ts
  • app/(apps)/audio/api/transcribe/route.ts
  • app/(apps)/audio/api/summarize/route.ts
  • app/(apps)/audio/components/*

​
Verification

Your setup is working if:
  • you can upload or record audio
  • transcription completes successfully
  • a summary can be generated
  • recordings remain available after refresh