app.py

import gradio as gr
# from TTS.api import TTS

# tts = TTS(model_name="tts_models/multilingual/multi-dataset/your_tts", progress_bar=False, gpu=False)

# def predict(text):
#     file_path = "output.wav"
#     tts.tts_to_file(text, speaker=tts.speakers[0], language="en", file_path=file_path)
#     return file_path

# demo = gr.Interface(
#     fn=predict,
#     inputs='text',
#     outputs='audio'
# )


# demo.launch()


# import requests
# import time
# import tempfile
# import os

# token = os.environ['apikey']
# #discord_id = os.environ['discord-id']
# API_HOST = "https://labs-proxy.voicemod.net/"

# def download_file(url):
#     response = requests.get(url)
#     if response.status_code == 200:
#         with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
#             tmp_file.write(response.content)
#             tmp_file.flush()
#             return tmp_file.name
#     else:
#         print("Error: Unable to download file")

# def tts(text):
#     url = API_HOST + "api/v1/tts/create"
#     payload = {
#         "text": text[:200] if len(text) > 200 else text,
#         "voiceId": "6926ecc5-ff5e-47c6-912b-3ffdb880bf56" # Narrator
#     }
#     headers = {
#         'x-api-key': token,
#     }
#     response = requests.request("POST", url, headers=headers, json=payload)
#     jsonResp = response.json()

#     return gr.make_waveform(download_file(jsonResp['audioUrl']))

# demo = gr.Interface(
#     fn=tts,
#     inputs="text",
#     outputs="audio"
# )

# demo.launch()

import openai
import os
#from pymongo import MongoClient

api_key = os.environ.get("OPENAI_API_KEY")

def transcribe_audio(filepath):
    audio = open(filepath, "rb")
    transcript = openai.Audio.transcribe("whisper-1", audio)
    return transcript['text']
    

# Create a Gradio Tabbed Interface
iface = gr.Interface(
    fn=transcribe_audio,
    inputs= gr.Audio(source="upload", type="filepath"),
    outputs="text",
)


iface.launch()