voice_utils.py

import requests
import base64
import os
from dotenv import load_dotenv

load_dotenv()

HF_API_KEY = os.getenv("HF_API_KEY")

# -----------------------------
# Speech-to-Text (STT) using HuggingFace Whisper
# -----------------------------
def speech_to_text(audio_file):
    with open(audio_file, "rb") as f:
        audio_bytes = f.read()

    response = requests.post(
        "https://api-inference.huggingface.co/models/openai/whisper-small",
        headers={"Authorization": f"Bearer {HF_API_KEY}"},
        data=audio_bytes
    )

    if response.status_code == 200:
        result = response.json()
        return result.get("text", "Sorry, I couldn’t transcribe that.")
    else:
        print(f"STT request failed: {response.status_code} {response.text}")
        return "Speech recognition failed."

# -----------------------------
# Text-to-Speech (TTS) using Kitten TTS
# -----------------------------
def text_to_speech(text):
    url = "https://huggingface.co/KittenML/kitten-tts-nano-0.1/resolve/main/tts"
    payload = {"text": text}
    response = requests.post(url, json=payload)

    if response.status_code == 200:
        audio_base64 = response.json()["audio"]
        audio_bytes = base64.b64decode(audio_base64)
        output_path = "output_audio.wav"
        with open(output_path, "wb") as f:
            f.write(audio_bytes)
        return output_path
    else:
        print(f"TTS request failed: {response.status_code}")
        return None