From 02fc6f1d1616de98a566d6925f96061a86a114db Mon Sep 17 00:00:00 2001
From: Anish Sarkar <104695310+AnishSarkar22@users.noreply.github.com>
Date: Sun, 5 Apr 2026 17:26:03 +0530
Subject: [PATCH] feat: add audio transcription functionality to ETL pipeline

---
 .../app/etl_pipeline/parsers/__init__.py      |  0
 .../app/etl_pipeline/parsers/audio.py         | 34 +++++++++++++++++++
 2 files changed, 34 insertions(+)
 create mode 100644 surfsense_backend/app/etl_pipeline/parsers/__init__.py
 create mode 100644 surfsense_backend/app/etl_pipeline/parsers/audio.py

diff --git a/surfsense_backend/app/etl_pipeline/parsers/__init__.py b/surfsense_backend/app/etl_pipeline/parsers/__init__.py
new file mode 100644
index 000000000..e69de29bb
diff --git a/surfsense_backend/app/etl_pipeline/parsers/audio.py b/surfsense_backend/app/etl_pipeline/parsers/audio.py
new file mode 100644
index 000000000..cd49bafde
--- /dev/null
+++ b/surfsense_backend/app/etl_pipeline/parsers/audio.py
@@ -0,0 +1,34 @@
+from litellm import atranscription
+
+from app.config import config as app_config
+
+
+async def transcribe_audio(file_path: str, filename: str) -> str:
+    stt_service_type = (
+        "local"
+        if app_config.STT_SERVICE and app_config.STT_SERVICE.startswith("local/")
+        else "external"
+    )
+
+    if stt_service_type == "local":
+        from app.services.stt_service import stt_service
+
+        result = stt_service.transcribe_file(file_path)
+        text = result.get("text", "")
+        if not text:
+            raise ValueError("Transcription returned empty text")
+    else:
+        with open(file_path, "rb") as audio_file:
+            kwargs: dict = {
+                "model": app_config.STT_SERVICE,
+                "file": audio_file,
+                "api_key": app_config.STT_SERVICE_API_KEY,
+            }
+            if app_config.STT_SERVICE_API_BASE:
+                kwargs["api_base"] = app_config.STT_SERVICE_API_BASE
+            response = await atranscription(**kwargs)
+            text = response.get("text", "")
+            if not text:
+                raise ValueError("Transcription returned empty text")
+
+    return f"# Transcription of {filename}\n\n{text}"