Upload app.py

app.py

@@ -0,0 +1,100 @@
+import gradio as gr
+import requests
+import openai
+import asyncio
+from deepgram import Deepgram
+from vocode.streaming.models.transcriber import (
+    DeepgramTranscriberConfig,
+    PunctuationEndpointingConfig,
+)
+from vocode.streaming.models.agent import ChatGPTAgentConfig
+from vocode.streaming.models.message import BaseMessage
+from vocode.streaming.models.synthesizer import ElevenLabsSynthesizerConfig
+from vocode.streaming.transcriber.deepgram_transcriber import DeepgramTranscriber
+from vocode.streaming.agent.chat_gpt_agent import ChatGPTAgent
+from vocode.streaming.synthesizer.eleven_labs_synthesizer import ElevenLabsSynthesizer
+from vocode.streaming.streaming_conversation import StreamingConversation
+from vocode.helpers import create_streaming_microphone_input_and_speaker_output
+
+# Initialize API keys and voice IDs
+DEEPGRAM_API_KEY = "cc96b784b5b5b313336f4986cb29574f9e97e446"
+ELEVEN_LABS_API_KEY = "sk_b4fc90106fafc4cb986ca25c858b98b4a3aaa15b4b851d45"
+VOICE_ID = "GBv7mTt0atIp3Br8iCZE"
+OPENAI_API_KEY = "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"
+
+# Initialize OpenAI client
+client = openai.OpenAI(api_key=OPENAI_API_KEY)
+
+# Initialize Deepgram
+deepgram = Deepgram(DEEPGRAM_API_KEY)
+
+# Function to transcribe audio using Deepgram
+async def transcribe_audio(audio_file_path):
+    with open(audio_file_path, 'rb') as audio_file:
+        audio_data = audio_file.read()
+
+    response = await deepgram.transcription.prerecorded(
+        {"buffer": audio_data, "mimetype": "audio/wav"},
+        {'punctuate': True, 'language': 'en'}
+    )
+    transcription = response['results']['channels'][0]['alternatives'][0]['transcript']
+    return transcription
+
+# Function to generate content using OpenAI GPT-4
+def generate_content(input_text):
+    response = client.chat.completions.create(
+        model="gpt-4",
+        messages=[
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": input_text}
+        ]
+    )
+    generated_text = response.choices[0].message.content.strip()
+    return generated_text
+
+# Function to convert text to speech using Eleven Labs
+def text_to_speech(text):
+    url = f"https://api.elevenlabs.io/v1/text-to-speech/{VOICE_ID}"
+    headers = {
+        "Accept": "audio/mpeg",
+        "Content-Type": "application/json",
+        "xi-api-key": ELEVEN_LABS_API_KEY
+    }
+    data = {
+        "text": text,
+        "voice_settings": {
+            "stability": 0.75,
+            "similarity_boost": 0.75
+        }
+    }
+    response = requests.post(url, json=data, headers=headers)
+    
+    if response.status_code == 200:
+        with open("output.mp3", "wb") as f:
+            f.write(response.content)
+        return "output.mp3"
+    else:
+        return f"Error: {response.status_code} - {response.text}"
+
+# Main function to handle the entire process
+async def process_audio(audio):
+    transcription = await transcribe_audio(audio)
+    generated_text = generate_content(transcription)
+    audio_file = text_to_speech(generated_text)
+    return transcription, generated_text, audio_file
+
+# Gradio interface setup
+interface = gr.Interface(
+    fn=lambda audio: asyncio.run(process_audio(audio)),
+    inputs=gr.Audio(type="filepath", label="Speak into your microphone"),
+    outputs=[
+        gr.Textbox(label="Transcription Output"),
+        gr.Textbox(label="Generated Content"),
+        gr.Audio(label="Synthesized Speech")
+    ],
+    title="Speech-to-Text, Content Generation, and Text-to-Speech",
+    description="Speak into the microphone, and the system will transcribe your speech, generate content, and convert the generated text into speech."
+)
+
+# Launch the Gradio interface
+interface.launch()