Spaces:
Sleeping
Sleeping
File size: 2,913 Bytes
2f52392 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 |
import assemblyai as aai
from elevenlabs import generate, stream
from openai import OpenAI
class AI_Assistant:
def __init__(self):
aai.settings.api_key = "ASSEMBLYAI-API-KEY"
self.openai_client = OpenAI(api_key="OPENAI-API-KEY")
self.elevenlabs_api_key = "ELEVENLABS-API-KEY"
self.transcriber = None
# Context for food ordering in a restaurant
self.full_transcript = [
{"role": "system", "content": "You are a virtual assistant for a restaurant. Help customers with food ordering, menu inquiries, and table reservations."},
]
def start_transcription(self):
self.transcriber = aai.RealtimeTranscriber(
sample_rate=16000,
on_data=self.on_data,
on_error=self.on_error,
on_open=self.on_open,
on_close=self.on_close,
end_utterance_silence_threshold=1000,
)
self.transcriber.connect()
microphone_stream = aai.extras.MicrophoneStream(sample_rate=16000)
self.transcriber.stream(microphone_stream)
def stop_transcription(self):
if self.transcriber:
self.transcriber.close()
self.transcriber = None
def on_open(self, session_opened: aai.RealtimeSessionOpened):
print("Session ID:", session_opened.session_id)
def on_data(self, transcript: aai.RealtimeTranscript):
if not transcript.text:
return
if isinstance(transcript, aai.RealtimeFinalTranscript):
self.generate_ai_response(transcript)
else:
print(transcript.text, end="\r")
def on_error(self, error: aai.RealtimeError):
print("An error occurred:", error)
def on_close(self):
print("Session closed.")
def generate_ai_response(self, transcript):
self.stop_transcription()
self.full_transcript.append({"role": "user", "content": transcript.text})
print(f"\nCustomer: {transcript.text}\n")
response = self.openai_client.chat.completions.create(
model="gpt-3.5-turbo",
messages=self.full_transcript
)
ai_response = response.choices[0].message.content
self.generate_audio(ai_response)
self.start_transcription()
print("\nListening for the next input...\n")
def generate_audio(self, text):
self.full_transcript.append({"role": "assistant", "content": text})
print(f"\nAI Assistant: {text}")
audio_stream = generate(
api_key=self.elevenlabs_api_key,
text=text,
voice="Rachel",
stream=True
)
stream(audio_stream)
if __name__ == "__main__":
greeting = "Welcome to Gourmet Bistro! My name is Sandy. How may I assist you today?"
ai_assistant = AI_Assistant()
ai_assistant.generate_audio(greeting)
ai_assistant.start_transcription()
|