diff --git a/backend/Procfile b/backend/Procfile
new file mode 100644
index 00000000..3f32b904
--- /dev/null
+++ b/backend/Procfile
@@ -0,0 +1 @@
+web: gunicorn -c gunicorn_config.py app:app
diff --git a/backend/gunicorn_config.py b/backend/gunicorn_config.py
new file mode 100644
index 00000000..08291d2e
--- /dev/null
+++ b/backend/gunicorn_config.py
@@ -0,0 +1,44 @@
+"""Gunicorn configuration for Render deployment."""
+import os
+import multiprocessing
+
+# Bind to the port Render provides
+bind = f"0.0.0.0:{os.getenv('PORT', '10000')}"
+
+# Use uvicorn workers
+worker_class = "uvicorn.workers.UvicornWorker"
+
+# Single worker for memory efficiency on free tier
+workers = 1
+
+# Timeout for slow startup (10 minutes to allow for model loading)
+timeout = 600
+
+# Graceful timeout
+graceful_timeout = 30
+
+# Keepalive
+keepalive = 5
+
+# Logging
+accesslog = "-"
+errorlog = "-"
+loglevel = os.getenv("LOG_LEVEL", "info").lower()
+
+# Preload app (set to False for faster startup if needed)
+preload_app = True
+
+
+def on_starting(server):
+    """Called just before the master process is initialized."""
+    print(f"[GUNICORN] Starting on {bind}", flush=True)
+
+
+def on_reload(server):
+    """Called when worker is reloaded."""
+    print(f"[GUNICORN] Reloading workers", flush=True)
+
+
+def when_ready(server):
+    """Called just after the server is started."""
+    print(f"[GUNICORN] Server is ready. Accepting connections.", flush=True)
diff --git a/backend/render-build.sh b/backend/render-build.sh
index 4fdcb455..5ec39d5f 100644
--- a/backend/render-build.sh
+++ b/backend/render-build.sh
@@ -2,8 +2,22 @@
 set -euo pipefail
 
 python -m pip install --upgrade pip setuptools wheel
+
+# Check if podcast-only mode is enabled - skip heavy ML models if so
+ENABLED_FEATURES="${ALWRITY_ENABLED_FEATURES:-all}"
+IS_PODCAST_ONLY=false
+
+if [[ "$ENABLED_FEATURES" == "podcast" ]]; then
+    IS_PODCAST_ONLY=true
+    echo "🔊 Podcast-only mode detected - skipping spaCy/NLTK model download"
+fi
+
 python -m pip install --retries 10 --timeout 120 -r requirements.txt
 
-# Download required NLTK and spaCy models during build phase
-python -m spacy download en_core_web_sm
-python -m nltk.downloader punkt_tab stopwords averaged_perceptron_tagger
+# Download required NLTK and spaCy models during build phase (skip for podcast-only)
+if [[ "$IS_PODCAST_ONLY" == "false" ]]; then
+    python -m spacy download en_core_web_sm
+    python -m nltk.downloader punkt_tab stopwords averaged_perceptron_tagger
+else
+    echo "🔊 Skipping spaCy/NLTK download for podcast-only mode"
+fi
diff --git a/backend/requirements.txt b/backend/requirements.txt
index 9d695301..6331d35d 100644
--- a/backend/requirements.txt
+++ b/backend/requirements.txt
@@ -3,6 +3,8 @@ fastapi>=0.115.14
 starlette>=0.40.0,<0.47.0
 sse-starlette<3.0.0
 uvicorn>=0.24.0
+uvicorn[standard]>=0.24.0
+gunicorn>=21.0.0
 python-multipart>=0.0.6
 python-dotenv>=1.0.0
 loguru>=0.7.2