Frequent error for Auto-GPT TTS

[Hercules942]

I keep getting this error randomly, sometimes it works haphazardly for a bit, but most of the time I get this error. Usually the opening line is most likely to be voiced, but I've never had more than 2 lines voiced.

" 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
Error:
Traceback (most recent call last): File "C:\AI\Auto-GPT\scripts\main.py", line 96, in print_assistant_thoughts speak.say_text(assistant_thoughts_speak) File "C:\AI\Auto-GPT\scripts\speak.py", line 45, in say_text success = eleven_labs_speech(text) File "C:\AI\Auto-GPT\scripts\speak.py", line 27, in eleven_labs_speech playsound("speech.mpeg") File "C:\Users\joech\AppData\Roaming\Python\Python39\site-packages\playsound.py", line 72,
in _playsoundWin winCommand(u'open {}'.format(sound)) File "C:\Users\joech\AppData\Roaming\Python\Python39\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."

[Jaybob32]

I had this issue as well. I found someone else that downgraded the playsound with:
pip install playsound 1.2.2

this worked for me.

[foxyayt]

use this and it should work: pip install playsound==1.2.2

[redhousc]

Thanks it worked I was able to downgrade. Now let’s see if it reduces how often I get that error.

[Hercules942]

Thank you! This worked perfectly, haven't had a single error since

[Jaybob32]

Ahh, so sorry. I forgot the == I can barely install these things.

[Concubine]

I used the playsound==1.2.2 downgrade but now have this error after I hear the initial "would you like me to go back to.."

I believe the file isn't removed after being played.

Traceback (most recent call last): File "C:\Albert\AGPT\Auto-GPT\scripts\main.py", line 275, in <module> prompt = construct_prompt() ^^^^^^^^^^^^^^^^^^ File "C:\Albert\AGPT\Auto-GPT\scripts\main.py", line 178, in construct_prompt config = prompt_user() ^^^^^^^^^^^^^ File "C:\Albert\AGPT\Auto-GPT\scripts\main.py", line 192, in prompt_user print_to_console( File "C:\Albert\AGPT\Auto-GPT\scripts\main.py", line 30, in print_to_console speak.say_text(f"{title}. {content}") File "C:\Albert\AGPT\Auto-GPT\scripts\speak.py", line 45, in say_text success = eleven_labs_speech(text, voice_index) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Albert\AGPT\Auto-GPT\scripts\speak.py", line 25, in eleven_labs_speech with open("speech.mpeg", "wb") as f: ^^^^^^^^^^^^^^^^^^^^^^^^^ PermissionError: [Errno 13] Permission denied: 'speech.mpeg'

Anyone encountered this?

[Wladastic]

Closing due to old and probably fixed.
If this still occurs to you, try running "python -m pip install -r requirements.txt "