src/audio_gen.py

import os
from typing import List
import replicate
from dotenv import load_dotenv


load_dotenv()
replicate_client = replicate.Client(api_token= os.getenv("REPLICATE_API_KEY"))

def audio_generation(
    scripts: str,
    voice_id: str,
    speed: float,
    volume: float,
    pitch: int,
    emotion: str
    ):
    output = replicate_client.run(
        "minimax/speech-02-turbo",
        input={
            "text": f"""{scripts}""",
            "pitch": pitch,
            "speed": speed,
            "volume": volume,
            "bitrate": 128000,
            "channel": "mono",
            "emotion": emotion,
            "voice_id": voice_id,
            "sample_rate": 32000,
            "language_boost": "English",
            "english_normalization": True
        }
    )
    urls: List[str] = []
    if isinstance(output, list) and output:
        first = output[0]
        url = getattr(first, "url", str(first))
        urls = [url]
    elif isinstance(output, str):
        urls = [output]
    elif hasattr(output, "url"):
        urls = [getattr(output, "url")]
    if urls:
        return urls[0]