adri6336 / gpt-voice-conversation-chatbot Goto Github PK

Hi Adrian

I noticed it was taking ages for the transcription to happen, so I've just downloaded your most recent version, but it is still taking a very long time (up to a minute or longer for a short phrase). It often also just gets "stuck" in listening mode (green window) for a very long time.

What could be the cause?

Many thanks

After the initial welcome message from the AI, there's no pop up or way for me to record an input.

Any idea on a fix for this?

I saw the instructions only mention Windows + Linux, but figured I'd try it out anyway. I installed espeak with brew, but when I run main.py I get this trace:

Exception in thread Thread-1:
Traceback (most recent call last):
  File "/usr/local/Cellar/[email protected]/3.9.9/Frameworks/Python.framework/Versions/3.9/lib/python3.9/threading.py", line 973, in _bootstrap_inner
    self.run()
  File "/usr/local/Cellar/[email protected]/3.9.9/Frameworks/Python.framework/Versions/3.9/lib/python3.9/threading.py", line 910, in run
    self._target(*self._args, **self._kwargs)
  File "/Users/zswitten/gpt-voice-conversation-chatbot/main.py", line 98, in main_loop
    self.display = pygame.display.set_mode((500, 500), pygame.RESIZABLE)
pygame.error: NSWindow drag regions should only be invalidated on the Main Thread!
Assertion failed: (NSViewIsCurrentlyBuildingLayerTreeForDisplay() != currentlyBuildingLayerTree), function NSViewSetCurrentlyBuildingLayerTreeForDisplay, file NSView.m, line 13477.
Illegal instruction: 4

It is possible to change the voice recognition to another language, currently there is only English.
Only handwriting recognition works, then google tts reads correctly, but very slowly.

This could be a problem on my end, please excuse me if that's the case but Im new to this.

I have to run MVS as admin to make the playback work (Im not using Eleven Labs api), but it only generates three audio files and then starts giving the following error:

` Error 259 for command:
play ./messages/3-5-2023/6.mp3 wait
The driver cannot recognize the specified command parameter.

Error 263 for command:
    close ./messages/3-5-2023/6.mp3
The specified device is not open or is not recognized by MCI.

Failed to close the file: ./messages/3-5-2023/6.mp3
[i]: DETECTED LANGUAGE: en
[X] Error trying to speak: [Errno 13] Permission denied: './messages/3-5-2023/6.mp3'`

I have followed the instructions to install this project. I am using macOS with an Intel chip.
However, when I run "python main.py," I encounter an error.
pygame 2.5.2 (SDL 2.28.3, Python 3.11.0) Hello from the pygame community. https://www.pygame.org/contribute.html Traceback (most recent call last): File "/Users/phungvuong/Documents/coding/TestCode/chatgpt/Talk/gpt-voice-conversation-chatbot/main.py", line 8, in <module> from chatbot import * File "/Users/phungvuong/Documents/coding/TestCode/chatgpt/Talk/gpt-voice-conversation-chatbot/chatbot.py", line 11, in <module> from tts_functions import * File "/Users/phungvuong/Documents/coding/TestCode/chatgpt/Talk/gpt-voice-conversation-chatbot/tts_functions.py", line 11, in <module> from elevenlabs import generate, play, save ImportError: cannot import name 'generate' from 'elevenlabs' (/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/elevenlabs/__init__.py)

I am not sure if thats chatgpt API problems? for example if I asked to tell a story, the results are always broken, as if there is a limit of words in reply.. and I have to type "continue" to resume the chat..

Hello Adri6336 :D

I absolutely love your program, it includes everything i want pretty much, but the processing time of a prompt takes about 5 seconds every time.

Is there anything you can do to improve this delay?

Also, is there any way to choose a elevenlabs voice?

tyvm in advance!

Hi Friend,

Thank you for this. I tried to compile it in PS / Windows 11 and latest version of Python 3.11.2.

On another machine, I tried with 3.7.16. Seemed to work better but still got path errors, although I believe that is MY fault. Will uninstall 3.11.2 and reinstall full 3.7.16, update and run "pip install -r requirements.txt.

Here is the error I received.

PS C:\temp\gptVoice> pip install -r requirements.txt
Collecting playsound==1.2.2
Using cached playsound-1.2.2-py2.py3-none-any.whl (6.0 kB)
Collecting gTTS==2.3.1
Using cached gTTS-2.3.1-py3-none-any.whl (28 kB)
Collecting SpeechRecognition==3.9.0
Using cached SpeechRecognition-3.9.0-py2.py3-none-any.whl (32.8 MB)
Collecting pygame==2.1.2
Using cached pygame-2.1.2.tar.gz (10.1 MB)
Preparing metadata (setup.py) ... error
error: subprocess-exited-with-error

× python setup.py egg_info did not run successfully.
│ exit code: 1
╰─> [77 lines of output]

  WARNING, No "Setup" File Exists, Running "buildconfig/config.py"
  Using WINDOWS configuration...

  Traceback (most recent call last):
    File "<string>", line 2, in <module>
    File "<pip-setuptools-caller>", line 34, in <module>
    File "C:\Users\Corbin\AppData\Local\Temp\pip-install-uki_18n4\pygame_e253ab220ecf45f9bcdaee7a217e2017\setup.py", line 359, in <module>
      buildconfig.config.main(AUTO_CONFIG)
    File "C:\Users\Corbin\AppData\Local\Temp\pip-install-uki_18n4\pygame_e253ab220ecf45f9bcdaee7a217e2017\buildconfig\config.py", line 225, in main
      deps = CFG.main(**kwds)
             ^^^^^^^^^^^^^^^^
    File "C:\Users\Corbin\AppData\Local\Temp\pip-install-uki_18n4\pygame_e253ab220ecf45f9bcdaee7a217e2017\buildconfig\config_win.py", line 511, in main
      return setup_prebuilt_sdl2(prebuilt_dir)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    File "C:\Users\Corbin\AppData\Local\Temp\pip-install-uki_18n4\pygame_e253ab220ecf45f9bcdaee7a217e2017\buildconfig\config_win.py", line 471, in setup_prebuilt_sdl2
      DEPS.configure()
    File "C:\Users\Corbin\AppData\Local\Temp\pip-install-uki_18n4\pygame_e253ab220ecf45f9bcdaee7a217e2017\buildconfig\config_win.py", line 336, in configure
      from . import vstools
    File "C:\Users\Corbin\AppData\Local\Temp\pip-install-uki_18n4\pygame_e253ab220ecf45f9bcdaee7a217e2017\buildconfig\vstools.py", line 11, in <module>
      compiler.initialize()
    File "C:\Users\Corbin\AppData\Local\Programs\Python\Python311\Lib\site-packages\setuptools\_distutils\msvc9compiler.py", line 403, in initialize
      vc_env = query_vcvarsall(VERSION, plat_spec)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    File "C:\Users\Corbin\AppData\Local\Programs\Python\Python311\Lib\site-packages\setuptools\_distutils\msvc9compiler.py", line 281, in query_vcvarsall
      raise DistutilsPlatformError("Unable to find vcvarsall.bat")
  distutils.errors.DistutilsPlatformError: Unable to find vcvarsall.bat
  Making dir :prebuilt_downloads:
  Downloading... https://www.libsdl.org/release/SDL2-devel-2.0.18-VC.zip ed561079ec622b0bab5a9e02976f5d540b0622da
  Unzipping :prebuilt_downloads\SDL2-devel-2.0.18-VC.zip:
  Downloading... https://www.libsdl.org/projects/SDL_image/release/SDL2_image-devel-2.0.5-VC.zip 137f86474691f4e12e76e07d58d5920c8d844d5b
  Unzipping :prebuilt_downloads\SDL2_image-devel-2.0.5-VC.zip:
  Downloading... https://www.libsdl.org/projects/SDL_ttf/release/SDL2_ttf-devel-2.0.15-VC.zip 1436df41ebc47ac36e02ec9bda5699e80ff9bd27
  Unzipping :prebuilt_downloads\SDL2_ttf-devel-2.0.15-VC.zip:
  Downloading... https://www.libsdl.org/projects/SDL_mixer/release/SDL2_mixer-devel-2.0.4-VC.zip 9097148f4529cf19f805ccd007618dec280f0ecc
  Unzipping :prebuilt_downloads\SDL2_mixer-devel-2.0.4-VC.zip:
  Downloading... https://www.pygame.org/ftp/jpegsr9d.zip ed10aa2b5a0fcfe74f8a6f7611aeb346b06a1f99
  Unzipping :prebuilt_downloads\jpegsr9d.zip:
  Downloading... https://pygame.org/ftp/prebuilt-x64-pygame-1.9.2-20150922.zip 3a5af3427b3aa13a0aaf5c4cb08daaed341613ed
  Unzipping :prebuilt_downloads\prebuilt-x64-pygame-1.9.2-20150922.zip:
  copying into .\prebuilt-x64
  Path for SDL: prebuilt-x64\SDL2-2.0.18
  ...Library directory for SDL: prebuilt-x64/SDL2-2.0.18/lib/x64
  ...Include directory for SDL: prebuilt-x64/SDL2-2.0.18/include
  Path for FONT: prebuilt-x64\SDL2_ttf-2.0.15
  ...Library directory for FONT: prebuilt-x64/SDL2_ttf-2.0.15/lib/x64
  ...Include directory for FONT: prebuilt-x64/SDL2_ttf-2.0.15/include
  Path for IMAGE: prebuilt-x64\SDL2_image-2.0.5
  ...Library directory for IMAGE: prebuilt-x64/SDL2_image-2.0.5/lib/x64
  ...Include directory for IMAGE: prebuilt-x64/SDL2_image-2.0.5/include
  Path for MIXER: prebuilt-x64\SDL2_mixer-2.0.4
  ...Library directory for MIXER: prebuilt-x64/SDL2_mixer-2.0.4/lib/x64
  ...Include directory for MIXER: prebuilt-x64/SDL2_mixer-2.0.4/include
  Path for PORTMIDI: prebuilt-x64
  ...Library directory for PORTMIDI: prebuilt-x64/lib
  ...Include directory for PORTMIDI: prebuilt-x64/include
  DLL for SDL2: prebuilt-x64/SDL2-2.0.18/lib/x64/SDL2.dll
  DLL for SDL2_ttf: prebuilt-x64/SDL2_ttf-2.0.15/lib/x64/SDL2_ttf.dll
  DLL for SDL2_image: prebuilt-x64/SDL2_image-2.0.5/lib/x64/SDL2_image.dll
  DLL for SDL2_mixer: prebuilt-x64/SDL2_mixer-2.0.4/lib/x64/SDL2_mixer.dll
  DLL for portmidi: prebuilt-x64/lib/portmidi.dll
  Path for FREETYPE not found.
  ...Found include dir but no library dir in prebuilt-x64.
  Path for PNG not found.
  ...Found include dir but no library dir in prebuilt-x64.
  Path for JPEG not found.
  ...Found include dir but no library dir in prebuilt-x64.
  DLL for freetype: prebuilt-x64/SDL2_ttf-2.0.15/lib/x64/libfreetype-6.dll

  ---
  For help with compilation see:
      https://www.pygame.org/wiki/CompileWindows
  To contribute to pygame development see:
      https://www.pygame.org/contribute.html
  ---

  [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed

× Encountered error while generating package metadata.
╰─> See above for output.

note: This is an issue with the package mentioned above, not pip.
hint: See above for details.

Mentioned in #1, but I do want to use a custom voice.

Its actually pretty simple, if the user knows their voice ID which they can query the endpoint themselves for, they just swap EXAVITQu4vr4xnSDxMaL` with it. This works.

I could probably submit a PR for it myself, but how should I pass it in? Do you perhaps want to use argparse to parse the args as it is a bit cleaner than checking the length of argv and assuming positions and the like.

Edit: I am going to try to do some refactoring in general if that is okay, as you have a bunch of duplicated code between gptcli and main.py.

I cannot get it to work both on my stationary PC and on laptop. I got the same error:

File "C:\Program Files\Python311\Lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 353, in
main()
File "C:\Program Files\Python311\Lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 335, in main
json_out['return_val'] = hook(**hook_input['kwargs'])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Program Files\Python311\Lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 118, in get_requires_for_build_wheel
return hook(config_settings)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\drago\AppData\Local\Temp\pip-build-env-1aa9hrdo\overlay\Lib\site-packages\setuptools\build_meta.py", line 355, in get_requires_for_build_wheel
return self._get_build_requires(config_settings, requirements=['wheel'])
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\drago\AppData\Local\Temp\pip-build-env-1aa9hrdo\overlay\Lib\site-packages\setuptools\build_meta.py", line 325, in _get_build_requires
self.run_setup()
File "C:\Users\drago\AppData\Local\Temp\pip-build-env-1aa9hrdo\overlay\Lib\site-packages\setuptools\build_meta.py", line 507, in run_setup
super(_BuildMetaLegacyBackend, self).run_setup(setup_script=setup_script)
File "C:\Users\drago\AppData\Local\Temp\pip-build-env-1aa9hrdo\overlay\Lib\site-packages\setuptools\build_meta.py", line 341, in run_setup
exec(code, locals())
File "", line 359, in
File "C:\Users\drago\AppData\Local\Temp\pip-install-zpsl8dp8\pygame_9bb69c7b58aa4ce08e8462093e7d1456\buildconfig\config.py", line 225, in main
deps = CFG.main(**kwds)
^^^^^^^^^^^^^^^^
File "C:\Users\drago\AppData\Local\Temp\pip-install-zpsl8dp8\pygame_9bb69c7b58aa4ce08e8462093e7d1456\buildconfig\config_win.py", line 511, in main
return setup_prebuilt_sdl2(prebuilt_dir)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\drago\AppData\Local\Temp\pip-install-zpsl8dp8\pygame_9bb69c7b58aa4ce08e8462093e7d1456\buildconfig\config_win.py", line 471, in setup_prebuilt_sdl2
DEPS.configure()
File "C:\Users\drago\AppData\Local\Temp\pip-install-zpsl8dp8\pygame_9bb69c7b58aa4ce08e8462093e7d1456\buildconfig\config_win.py", line 336, in configure
from . import vstools
File "C:\Users\drago\AppData\Local\Temp\pip-install-zpsl8dp8\pygame_9bb69c7b58aa4ce08e8462093e7d1456\buildconfig\vstools.py", line 11, in
compiler.initialize()
File "C:\Users\drago\AppData\Local\Temp\pip-build-env-1aa9hrdo\overlay\Lib\site-packages\setuptools_distutils\msvc9compiler.py", line 403, in initialize
vc_env = query_vcvarsall(VERSION, plat_spec)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\drago\AppData\Local\Temp\pip-build-env-1aa9hrdo\overlay\Lib\site-packages\setuptools_distutils\msvc9compiler.py", line 281, in query_vcvarsall
raise DistutilsPlatformError("Unable to find vcvarsall.bat")
distutils.errors.DistutilsPlatformError: Unable to find vcvarsall.bat
[end of output]

note: This error originates from a subprocess, and is likely not a problem with pip.
error: subprocess-exited-with-error

× Getting requirements to build wheel did not run successfully.
│ exit code: 1
╰─> See above for output.

I tried installing MS C++, Visual Studio, but issue persists. Any ideas?

I have this project running on Ubuntu Server 22 VM if it matters. I also connected to Windows 11 via ssh, but it doesn't detect the microphone either.
Is the mic detected automatically from the system or do I have to mark something manually? Or I have to run it on a desktop machine.

vm@ai:/python/gpt-voice-conversation-chatbot$ python3 main.py
pygame 2.1.2 (SDL 2.0.16, Python 3.10.6)
Hello from the pygame community. https://www.pygame.org/contribute.html
[OK] NLTK Loaded
ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM sysdefault
ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM sysdefault
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.front
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.rear
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.center_lfe
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.side
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround21
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround21
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround40
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround41
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround50
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround51
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.surround71
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.iec958
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.iec958
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.iec958
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.hdmi
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.modem
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM cards.pcm.phoneline
ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_id returned error: No such file or directory
ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM dmix
Cannot connect to server socket err = No such file or directory
Cannot connect to server request channel
jack server is not running or cannot be started
JackShmReadWritePtr::~JackShmReadWritePtr - Init not done for -1, skipping unlock
JackShmReadWritePtr::~JackShmReadWritePtr - Init not done for -1, skipping unlock
Traceback (most recent call last):
  File "/python/gpt-voice-conversation-chatbot/main.py", line 505, in <module>
    gui = GUI()
  File "/python/gpt-voice-conversation-chatbot/main.py", line 103, in __init__
    self.mic = sr.Microphone()
  File "/home/vm/.local/lib/python3.10/site-packages/speech_recognition/__init__.py", line 99, in __init__
    device_info = audio.get_device_info_by_index(device_index) if device_index is not None else audio.get_default_input_device_info()
  File "/usr/lib/python3/dist-packages/pyaudio.py", line 949, in get_default_input_device_info
    device_index = pa.get_default_input_device()
OSError: No Default Input Device Available

sorry for being a noob

Hi again :)

So I wonder if it's feasible to make it so the bot is continuously listening to the mic, instead of triggering the recording for every prompt?
The conversation would feel much more natural and fluid if it didn't require pressing any buttons.
Perhaps you are familiar with Neuro-sama AI VTuber which seems to listen to conversation partners all the time but since its creator made it its job, he doesn't want to share details how it works exactly.

Perhaps to start with we could have it so after the TTS of choice stops talking back to us, automatically triggers recording again?
I think it would require either removing the time window during which you need to say your prompt as currently recording stops after short while if you don't speak or at least prolonging that window significantly.

Just some food for thoughts. I really like the project and would love to see it grow and get even better than it already is!

Hey there! Awesome work =)

• Could you add support for using Custom Cloned Elevenlabs voices? Thank You!
• It would also be cool to have an 'always listening' option to toggle (or say out loud)
• Ability to automatically select Elevenlabs as the default on launch (I'm unable to switch back to Elevenlabs after restarting even with the voice command for some reason)

My intention is to use this as an easy gateway for creating an A.I Virtual Content Creator like Neuro-Sama / or Nothing, Forever
https://www.youtube.com/watch?v=yn0iVOtr6FE&t=120s | https://youtu.be/jAWS3K_3jqQ?t=58

Hi there,

I wanted to check if it's possible to reduce the latency so the conversations are more natural and fluid. Currently there is around 30 seconds delay between I finish my input (bot no longer listens and goes blue color) and the output answer from Elevenlabs.
I tested the default TTS and the response time was about half of that so I assume it's just because of Elevanlabs but I am no programmer so I don't know if this can be anyhow improved on your end.

Note - paid version of OpenAI (ChatGPT Plus) says that the response is faster. Do you know how significant uplift this may give in this case?

When I press and hold space and start speaking, once I pause and start thinking about how to speak, soon, the conversation mode will be closed and the conversation will be submitted to chatgpt. This is very unnatural, shouldn't it wait for the user to release the space before handing over what the user said to chatgpt? Just a little advice. I like your project, but there do exist some problems.