Successful implementation of TTS on Google Colab

API
,
1

Hi Team,

I made a small tweak to the provided TTS code from OpenAI documentation page and it worked. The output is an embedded audio file on which I manually clicked ’ Play’. Try this code:

import io
from openai import OpenAI
from pydub import AudioSegment
from pydub.playback import play
from dotenv import load_dotenv, find_dotenv
from IPython.display import Audio, display

load_dotenv(find_dotenv(), override=True)

client = OpenAI()
if __name__ == "__main__":

text = input("Enter text: ")

response = client.audio.speech.create(

model="tts-1",

voice="alloy",

input=text,

)

# Convert the binary response content to a byte stream

byte_stream = io.BytesIO(response.content)

# Read the audio data from the byte stream

audio = AudioSegment.from_file(byte_stream, format="mp3")

audio
1 Like