diff --git a/README.md b/README.md
index 2adceaf..9b95a9a 100644
--- a/README.md
+++ b/README.md
@@ -15,12 +15,14 @@ Monitor the Berlin Perso/Passport portal, crack the audio CAPTCHA with Whisper,
 - Firefox + `geckodriver` in `$PATH` for Selenium
 - `ffmpeg` (needed by `openai-whisper`)
 - Optional: Tesseract OCR if you experiment with the image-based approach in `ocr/`
+- Optional: Python packages from `requirements-ocr.txt` when working on the OCR experiments
 
 ## Setup
 1. Clone the repo and create a virtual environment: `python -m venv .venv && source .venv/bin/activate`
 2. Install runtime dependencies: `pip install -r requirements.txt`
-3. (Optional) Add tooling such as pytest: `pip install -r dev-requirements.txt`
-4. Provide credentials:
+3. (Optional) Install OCR extras: `pip install -r requirements-ocr.txt`
+4. (Optional) Add tooling such as pytest: `pip install -r dev-requirements.txt`
+5. Provide credentials:
 	- Copy `settings.example.py` to `settings.py`
 	- Set `DOCUMENT_ID` (the identifier embedded in the Berlin status URL)
 	- Set `WEBHOOK_URL` pointing to the service that should receive status payloads
diff --git a/requirements-ocr.txt b/requirements-ocr.txt
new file mode 100644
index 0000000..1cce72d
--- /dev/null
+++ b/requirements-ocr.txt
@@ -0,0 +1,14 @@
+# Optional OCR dependencies
+
+# traditional OCR
+pillow
+pytesseract
+opencv-python
+tqdm
+streamlit
+python-Levenshtein
+
+# ocr with keras/tensorflow
+tensorflow
+keras
+matplotlib
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
index 2a7d88d..5e89b6e 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,15 +5,5 @@ beautifulsoup4
 # audio processing
 openai-whisper
 
-# traditional OCR
-pillow
-pytesseract
-opencv-python
-tqdm
-streamlit
-python-Levenshtein
-
-# ocr with keras/tensorflow
-tensorflow
-keras
-matplotlib
\ No newline at end of file
+# for sending results to webhook
+requests