Upload 3 files

README.md

@@ -1,14 +1,9 @@
----
-title: FluentQ
-emoji: 🦀
-colorFrom: yellow
-colorTo: red
-sdk: gradio
-sdk_version: 5.24.0
-app_file: app.py
-pinned: false
-license: apache-2.0
-short_description: AGI over telecom demo
----
+# AGI Telecom POC
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+This is a full stack voice interface system powered by LLM, STT, TTS, and WebRTC-ready frontend.
+
+## Quick Start
+```bash
+pip install -r requirements.txt
+uvicorn app.main:app --reload
+```

app.py

@@ -0,0 +1,41 @@
+import gradio as gr
+from fastapi import FastAPI, UploadFile, File, Request
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import StreamingResponse
+from fastapi.staticfiles import StaticFiles
+from app.agent import process_text
+from app.speech_to_text import transcribe_audio
+from app.text_to_speech import synthesize_speech
+import io
+
+app = FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+app.mount("/", StaticFiles(directory="frontend", html=True), name="frontend")
+
+@app.post("/transcribe")
+async def transcribe(file: UploadFile = File(...)):
+    audio_bytes = await file.read()
+    text = transcribe_audio(audio_bytes)
+    return {"transcription": text}
+
+@app.post("/query")
+async def query_agent(request: Request):
+    data = await request.json()
+    input_text = data.get("input_text", "")
+    response = process_text(input_text)
+    return {"response": response}
+
+@app.get("/speak")
+async def speak(text: str):
+    audio = synthesize_speech(text)
+    return StreamingResponse(io.BytesIO(audio), media_type="audio/wav")
+
+# Required for Hugging Face Spaces
+gradio_app = gr.mount_gradio_app(app, None)

requirements.txt

@@ -0,0 +1,7 @@
+gradio
+fastapi
+uvicorn
+python-multipart
+openai-whisper
+llama-cpp-python
+edge-tts