bots/speaking.py

import whisper
from gtts import gTTS
from pydub import AudioSegment

import os
from llamaapi import LlamaAPI
from openai import OpenAI
from loguru import logger

# Initialize
llama = LlamaAPI("LL-AirERHEk0jLIE1yEPvMXeobNfLsqLWJWcxLRS53obrZ3XyqMTfZc4EAuOs7r3wso")

api_key = "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"
os.environ["OPENAI_API_KEY"] = api_key
client = OpenAI()


def convert_to_mp3(input_path, output_path):
    audio = AudioSegment.from_file(input_path)

    audio.export(output_path, format="mp3")
    print(f"Audio converted to MP3 and saved as: {output_path}")


# convert_to_mp3("/content/audio_input.wav", "/content/audio_input.mp3")


def transcribe_audio(audio_path):
    """
    Transcribes audio to text using Whisper.

    Parameters:
    - audio_path (str): The path to the audio file.

    Returns:
    - str: The transcribed text.
    """
    model = whisper.load_model("base")
    audio = whisper.load_audio(audio_path)
    audio = whisper.pad_or_trim(audio)
    mel = whisper.log_mel_spectrogram(audio).to(model.device)

    _, probs = model.detect_language(mel)
    print(f"Detected language: {max(probs, key=probs.get)}")

    options = whisper.DecodingOptions()
    result = model.decode(mel, options)
    logger.success(f'Detecting completed, result: {result.text}')
    return result.text


def text_to_speech(text, filename="/content/response.mp3"):
    """
    Converts text to speech using gTTS and saves the audio file.

    Parameters:
    - text (str): The text to convert to speech.
    - filename (str): The filename for the saved audio file.
    """
    tts = gTTS(text=text, lang='en')
    tts.save(filename)
    # display(Audio(filename))
    # os.remove(filename)  # Optionally remove the file after playing


def audio_chat_with_model(prompt, model_type="gpt-4"):

    if model_type == "gpt-4":
        try:
            chat_completion = client.chat.completions.create(
                model="gpt-4",
                messages=[
                    {"role": "system", "content": "Imagine you're a supportive language tutor engaging in a conversation with an ESL learner. "
                    "Learner is interested in discussing a variety of topics to improve their English speaking skills. "
                    "Your goal is to encourage learners to speak as much as possible, gently correct any mistakes, and provide constructive feedback."
                    "Adapt your conversation to include vocabulary and grammatical structures relevant to the discussion, ensuring a rich, engaging dialogue. "
                    "Correct errors in a positive manner and encourage the learner to ask questions and express opinions freely. "
                    "Conclude with a summary of their strengths during the session and offer specific advice for continued language improvement."},
                    {"role": "user", "content": prompt},
                ]
            )
            return chat_completion.choices[0].message.content.strip()
        except Exception as e:
            return f"An error occurred with GPT-4: {e}"