Upload pocket-recorder MP3s, extract ID3 metadata, and transcribe them with OpenAI Whisper, a local faster-whisper server, or a remote OpenAI-compatible endpoint.

Built with Laravel 13, Blade, Tailwind CSS 4, and Laravel AI.

Features

Upload MP3s (up to 100 MB) and store them on the local disk
Automatic ID3 metadata extraction (title, artist, album, duration, recorded date)
Search recordings by title, artist, or transcript
Queued transcription with three engines:
- Cloud — OpenAI Whisper (whisper-1)
- Local — confidential; OpenAI-compatible faster-whisper-server (e.g. Docker on this machine)
- Ollama host — user-supplied host URL exposing /v1/audio/transcriptions
Copy finished transcripts from the recording detail page

Requirements

PHP 8.3+ (8.5 recommended)
Composer
Node.js & npm
SQLite (default) or another supported database
For cloud transcription: an OpenAI API key
For local transcription: a running faster-whisper-server
For remote transcription: a host with an OpenAI-compatible transcription API

Setup

composer setup

That installs PHP and JS dependencies, copies .env if needed, generates the app key, runs migrations, and builds frontend assets.

Or step by step:

composer install
cp .env.example .env
php artisan key:generate
touch database/database.sqlite   # if using SQLite
php artisan migrate
npm install
npm run build

Configuration

Copy values from .env.example. The transcription-related settings are:

Variable	Purpose
`OPENAI_API_KEY`	Required for cloud Whisper
`OPENAI_URL`	OpenAI API base URL (default `https://api.openai.com/v1`)
`LOCAL_WHISPER_URL`	Local faster-whisper base URL (default `http://localhost:8000/v1`)
`LOCAL_WHISPER_API_KEY`	API key for local server (often unused)
`LOCAL_WHISPER_MODEL`	Model name for local transcription
`REMOTE_WHISPER_MODEL`	Model name for Ollama-host transcription
`TRANSCRIPTION_TIMEOUT`	Job/HTTP timeout in seconds (default `600`)
`QUEUE_CONNECTION`	Use `database` (default) so transcription runs in the background

Ensure APP_URL matches how you access the app (default http://localhost:8000).

Running locally

Start the app, queue worker, and Vite together:

composer run dev

Or separately:

php artisan serve
php artisan queue:work
npm run dev

Open http://localhost:8000/recordings.

Transcription jobs are queued — keep a queue worker running or jobs will stay pending.

Usage

Upload an MP3 from Recordings → Upload (optional title override).
Open the recording and choose a transcription engine.
Wait for the queue job to finish, then refresh to view or copy the transcript.
Search the list by title, artist, or transcript text.

Transcription engines

Driver	When to use	Needs
`cloud`	Fastest path; audio leaves your machine	`OPENAI_API_KEY`
`local`	Confidential; audio stays on this machine	faster-whisper-server at `LOCAL_WHISPER_URL`
`ollama`	Another machine on your network	Host URL + OpenAI-compatible `/v1/audio/transcriptions`

Tests

composer test
# or
php artisan test

License

MIT