---
title: "Quickstart"
description: "Upload audio, wait for transcription, and generate Insights."
---

## 1. Check authentication

```bash
curl https://audream-api.tulingbc.com/v1/auth/me \
  -H "Authorization: Bearer $AUDREAM_API_KEY"
```

## 2. Upload audio

Generate a UUID for the note, then submit the audio file:

```bash
NOTE_ID=$(uuidgen | tr '[:upper:]' '[:lower:]')

curl -X POST \
  "https://audream-api.tulingbc.com/v1/notes/$NOTE_ID/transcription" \
  -H "Authorization: Bearer $AUDREAM_API_KEY" \
  -F "file=@meeting.m4a" \
  -F "title=Product review" \
  -F "language=auto" \
  -F "auto_speaker_labeling_enabled=true"
```

The API returns `202 Accepted` while processing runs asynchronously.

## 3. Poll transcription

```bash
curl "https://audream-api.tulingbc.com/v1/notes/$NOTE_ID/transcription" \
  -H "Authorization: Bearer $AUDREAM_API_KEY"
```

- `200` means transcription is complete.
- `202` means processing is still active.
- `422` means transcription failed; read the response `detail`.

## 4. Generate Insights

After transcription succeeds, send the transcription object to the Insights endpoint:

```bash
curl -X POST \
  "https://audream-api.tulingbc.com/v1/notes/$NOTE_ID/insights" \
  -H "Authorization: Bearer $AUDREAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d @insights-request.json
```

See [Audio to Insights](/guides/audio-to-insights) for a complete Python example that performs this flow automatically.