feat: external stt

backend/apps/audio/main.py

@@ -240,6 +240,7 @@ def transcribe(
             f.write(contents)
             f.close()
 
+        if app.state.config.STT_ENGINE == "":
             whisper_kwargs = {
                 "model_size_or_path": WHISPER_MODEL,
                 "device": whisper_device_type,
@@ -274,6 +275,39 @@ def transcribe(
 
             return {"text": transcript.strip()}
 
+        elif app.state.config.STT_ENGINE == "openai":
+            headers = {"Authorization": f"Bearer {app.state.config.STT_OPENAI_API_KEY}"}
+
+            files = {"file": (filename, open(file_path, "rb"))}
+            data = {"model": "whisper-1"}
+
+            r = None
+            try:
+                r = requests.post(
+                    url=f"{app.state.config.STT_OPENAI_API_BASE_URL}/audio/transcriptions",
+                    headers=headers,
+                    files=files,
+                    data=data,
+                )
+
+                r.raise_for_status()
+                return r.json()
+            except Exception as e:
+                log.exception(e)
+                error_detail = "Open WebUI: Server Connection Error"
+                if r is not None:
+                    try:
+                        res = r.json()
+                        if "error" in res:
+                            error_detail = f"External: {res['error']['message']}"
+                    except:
+                        error_detail = f"External: {e}"
+
+                raise HTTPException(
+                    status_code=r.status_code if r != None else 500,
+                    detail=error_detail,
+                )
+
     except Exception as e:
         log.exception(e)