Upload 2 files

app.py

@@ -0,0 +1,124 @@
+import os
+import base64
+import uuid
+import gradio as gr
+from openai import OpenAI
+from speechify import Speechify
+from dotenv import load_dotenv
+
+# Detect Hugging Face environment
+RUNNING_IN_SPACES = os.getenv("SYSTEM") == "spaces"
+
+# Load API keys
+if not RUNNING_IN_SPACES:
+    load_dotenv()
+openai_api_key = os.getenv("OPENAI_API_KEY")
+speechify_api_key = os.getenv("SPEECHIFY_API_KEY")
+
+# Sanity check (but don't print full keys)
+print(f"✅ OPENAI_API_KEY loaded: {'✅' if openai_api_key else '❌ MISSING'}")
+print(f"✅ SPEECHIFY_API_KEY loaded: {'✅' if speechify_api_key else '❌ MISSING'}")
+
+# Initialize clients
+openai_client = OpenAI(api_key=openai_api_key)
+speechify_client = Speechify(token=speechify_api_key)
+
+# Voice config
+language_config = {
+    "Portuguese": {
+        "voice_id": "joao",
+        "language": "pt-PT",
+        "model": "simba-multilingual",
+        "audio_format": "mp3"
+    },
+    "French": {
+        "voice_id": "leo",
+        "language": "fr-FR",
+        "model": "simba-multilingual",
+        "audio_format": "mp3"
+    },
+    "Spanish": {
+        "voice_id": "danna-sofia",
+        "language": "es-MX",
+        "model": "simba-multilingual",
+        "audio_format": "mp3"
+    },
+}
+
+# Function for chat + TTS
+def chat_and_speak(user_input, language_choice):
+    gpt_response = ""
+    audio_output_path = None
+    try:
+        if not user_input or not user_input.strip():
+            return "Please enter some text to process.", None
+
+        print(f"🧠 User input: {user_input}")
+        print(f"🗣️ Language choice: {language_choice}")
+
+        # Step 1: Get GPT response
+        system_message = f"You are a friendly {language_choice} language tutor. Respond only in {language_choice}."
+        completion = openai_client.chat.completions.create(
+            model="gpt-4",
+            messages=[
+                {"role": "system", "content": system_message},
+                {"role": "user", "content": user_input}
+            ]
+        )
+        gpt_response = completion.choices[0].message.content
+        print(f"💬 GPT response: {gpt_response}")
+
+        # Step 2: Use Speechify to generate audio
+        config = language_config.get(language_choice)
+        if not config:
+            error_msg = f"⚠️ Language '{language_choice}' not supported."
+            print(error_msg)
+            return f"{gpt_response}\n\n{error_msg}", None
+
+        tts_response = speechify_client.tts.audio.speech(
+            input=gpt_response,
+            voice_id=config["voice_id"],
+            model=config["model"],
+            audio_format=config["audio_format"]
+        )
+
+        if hasattr(tts_response, "audio_data") and isinstance(tts_response.audio_data, str) and tts_response.audio_data:
+            try:
+                audio_bytes = base64.b64decode(tts_response.audio_data)
+                os.makedirs("speech_files", exist_ok=True)
+                audio_output_path = os.path.join("speech_files", f"speech_{uuid.uuid4().hex}.mp3")
+                with open(audio_output_path, "wb") as f:
+                    f.write(audio_bytes)
+            except Exception as audio_err:
+                print(f"🔥 Error processing audio data: {audio_err}")
+                return f"{gpt_response}\n\n⚠️ Error saving audio: {audio_err}", None
+        else:
+            print("⚠️ No audio data received from Speechify or audio_data is not a string.")
+            return f"{gpt_response}\n\n⚠️ No audio data received from Speechify.", None
+
+        return gpt_response, audio_output_path
+
+    except Exception as e:
+        print(f"🔥 An unexpected error occurred: {e}")
+        error_message = f"⚠️ An unexpected error occurred: {e}"
+        if gpt_response:
+            return f"{gpt_response}\n\n{error_message}", None
+        return error_message, None
+
+# Gradio interface
+iface = gr.Interface(
+    fn=chat_and_speak,
+    inputs=[
+        gr.Textbox(label="Say something"),
+        gr.Dropdown(choices=["Portuguese", "French", "Spanish"], value="Portuguese", label="Language"),
+    ],
+    outputs=[
+        gr.Textbox(label="GPT Response"),
+        gr.Audio(label="TTS Playback", type="filepath")
+    ],
+    title="Language Tutor with GPT and Speechify",
+    allow_flagging="never"
+)
+
+if __name__ == "__main__":
+    iface.launch()

requirements.txt

@@ -0,0 +1,63 @@
+aiofiles==24.1.0
+annotated-types==0.7.0
+anyio==4.9.0
+audioop-lts==0.2.1
+certifi==2024.6.2
+charset-normalizer==3.3.2
+click==8.1.8
+distro==1.9.0
+fastapi==0.115.13
+ffmpy==0.6.0
+filelock==3.18.0
+fsspec==2025.5.1
+gradio==5.34.0
+gradio_client==1.10.3
+groovy==0.1.2
+gTTS==2.5.4
+h11==0.16.0
+hf-xet==1.1.4
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.33.0
+idna==3.7
+Jinja2==3.1.6
+jiter==0.10.0
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+mdurl==0.1.2
+numpy==2.3.0
+openai==1.88.0
+orjson==3.10.18
+packaging==25.0
+pandas==2.3.0
+pillow==11.2.1
+pydantic==2.11.7
+pydantic_core==2.33.2
+pydub==0.25.1
+Pygments==2.19.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.0
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+requests==2.32.3
+rich==14.0.0
+ruff==0.12.0
+safehttpx==0.1.6
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+speechify==0.0.0
+speechify-api==1.2.0
+starlette==0.46.2
+tabulate==0.9.0
+tomlkit==0.13.3
+tqdm==4.67.1
+typer==0.16.0
+typing-inspection==0.4.1
+typing_extensions==4.14.0
+tzdata==2025.2
+urllib3==2.2.2
+uvicorn==0.34.3
+websockets==15.0.1