Error 263 for command: open speech.mpeg

[MoreTore]

Duplicates

• I have searched the existing issues

Steps to reproduce 🕹

It seems that trying to call say_text() twice will cause the issue.
Running on Windows 11.
Python 3.10.10
PS D:\Projects\Auto-GPT> python scripts/main.py --speak --gpt3only

import os
from playsound import playsound
import requests
from config import Config
cfg = Config()
import gtts


# TODO: Nicer names for these ids
voices = ["ErXwobaYiN019PkySvjV", "EXAVITQu4vr4xnSDxMaL"]

tts_headers = {
    "Content-Type": "application/json",
    "xi-api-key": cfg.elevenlabs_api_key
}

def eleven_labs_speech(text, voice_index=0):
    tts_url = "https://api.elevenlabs.io/v1/text-to-speech/{voice_id}".format(
        voice_id=voices[voice_index])
    formatted_message = {"text": text}
    response = requests.post(
        tts_url, headers=tts_headers, json=formatted_message)

    if response.status_code == 200:
        with open("speech.mpeg", "wb") as f:
            f.write(response.content)
        playsound("speech.mpeg")
        os.remove("speech.mpeg")
        return True
    else:
        print("Request failed with status code:", response.status_code)
        print("Response content:", response.content)
        return False

def gtts_speech(text):
    tts = gtts.gTTS(text)
    tts.save("speech.mp3")
    playsound("speech.mp3")
    os.remove("speech.mp3")

def say_text(text, voice_index=0):
    if not cfg.elevenlabs_api_key:
        gtts_speech(text)
    else:
        success = eleven_labs_speech(text, voice_index)
        if not success:
            gtts_speech(text)

if __name__ == "__main__":
    say_text("Hello, this")
    say_text("Hello, this")

Current behavior 😯

When using speak mode, it works for a random number of times but then eventually leads to this error.

Speak Mode: ENABLED
GPT3.5 Only Mode: ENABLED
Welcome to Auto-GPT! Enter the name of your AI and its role below. Entering nothing will load defaults.
Name your AI: For example, 'Entrepreneur-GPT'
AI Name: Realestate-GPT

Error 263 for command:
    open speech.mpeg
The specified device is not open or is not recognized by MCI.

Error 263 for command:
    close speech.mpeg
The specified device is not open or is not recognized by MCI.

Failed to close the file: speech.mpeg
Traceback (most recent call last):
File "D:\Projects\Auto-GPT\scripts\main.py", line 275, in
prompt = construct_prompt()
File "D:\Projects\Auto-GPT\scripts\main.py", line 178, in construct_prompt
config = prompt_user()
File "D:\Projects\Auto-GPT\scripts\main.py", line 207, in prompt_user
print_to_console(
File "D:\Projects\Auto-GPT\scripts\main.py", line 30, in print_to_console
speak.say_text(f"{title}. {content}")
File "D:\Projects\Auto-GPT\scripts\speak.py", line 45, in say_text
success = eleven_labs_speech(text, voice_index)
File "D:\Projects\Auto-GPT\scripts\speak.py", line 27, in eleven_labs_speech
playsound("speech.mpeg")
File "C:\Users\faste\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\playsound.py", line 72, in _playsoundWin
winCommand(u'open {}'.format(sound))
File "C:\Users\faste\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.10_qbz5n2kfra8p0\LocalCache\local-packages\Python310\site-packages\playsound.py", line 64, in winCommand
raise PlaysoundException(exceptionMessage)
playsound.PlaysoundException:
Error 263 for command:
open speech.mpeg
The specified device is not open or is not recognized by MCI.

Expected behavior 🤔

it should speak

Your prompt 📝

# Paste your prompt here

[MoreTore]

GPT4 says

The error you're encountering might be caused by the playsound library not releasing the file properly after playing the sound. To resolve this issue, you can use a different method to play the sound, such as using the pydub library with the simpleaudio playback module.

[MoreTore]

Solution!

pip uninstall playsound
pip install playsound==1.2.2

[ThirdDemented]

+1!