senols

Ah i see. You are using image generator module..

I already implemented different sizing options for image generator in Content Writer but not yet for that module.

probably we can add default size options under Image Generator – Settings tab so that you can customize it from there.

I will check this.. thanks for the report.

Hi @bonfort,

I tested Google tts on my side and it is working, so i am assuming this is likely a setup or API access issue.

Please check the following:

1. In AI Puffer > Settings > AI, select Google and confirm that a Google API key is saved and models synced.

2. In your Google Cloud Console, make sure the same project/API key has Cloud Text-to-Speech API enabled. Google/Gemini access alone may not be enough for TTS.

3. Confirm billing and quota are active for your Google Cloud project.

4. In AI Puffer > Chatbots > your chatbot > Tools, make sure Text to Speech is enabled and open tts options and confirm: Provider is set to Google. A Google voice is selected, not the empty “Select Voice” option.

If it still fails, open browser DevTools > Network, click the play button, and check the admin-ajax.php request for aipkit_generate_speech. Please send me the error message shown there.

The most common causes are: tts API not enabled in Google Cloud, missing/incorrect Google API key, API key restrictions, billing/quota issues, or no Google voice saved for that specific chatbot.

pls let me know how it goes.

Hi @ambienbuyxxxykki7865643

I am sorry to hear that you are not satisfied with the plugin.

Regarding the refund requests, we usually fulfill those requests within 24 hours.

Since we are not allowed to discuss paid plan related topics on WP forums, could you pls send us an email at [email protected] ?

Pls make sure to include your subscription details and we will take it from there.

Hi @alwaysenthusiast

Just curios, was this resolved?

hi @alwaysenthusiast

The error “Could not resolve host: api.openai.com” is a DNS (Domain Name System) issue where your computer or server cannot translate the domain name into an IP address.

Was there any change in your network settings?

hi @adrian87nn

i will help you to fix the issue.

could you some information about your chatbot settings;

1. did you enable popup mode?
2. did you select an icon for the widget?
3. which caching plugin are you using? did you clear your cache?
4. if you are comfortable to share your website pls share it here so i can check. it not i responses your email pls check your spam folder.

if you can also share some screenshots from your bot settings that would be great.

pls note that there is no restriction. this is probably a cache or misconfiguration.

waiting for your response.

by the way if you can switch to nginx from apache that will also fix the issue.

Hi @alwaysenthusiast

Thanks for sharing the server details.

The reason streaming is not working as expected on your site is this server setup:

PHP SAPI: fpm-fcgi

What that means:

– your site is running PHP through PHP-FPM / FastCGI instead of direct PHP output
– this setup is normally fast and efficient
– however, on many servers it also buffers the response before sending it to the browser

That buffering is important here because chatbot streaming depends on the server sending small chunks immediately as they are generated.

So instead of:

– chunk 1
– chunk 2
– chunk 3

your server is holding everything in memory and only release it when the request is finished. That is why on your site the reply appears all at once instead of streaming live.

This buffering can also make timeouts more likely with heavier models like gpt-5.4, because the request stays open longer and the browser/server waits for the full response.

Possible fixes:

– ask your hosting provider to disable FastCGI / proxy buffering
– if they use Apache with PHP-FPM, they should check FastCGI/proxy buffering and flush behavior
– disable PHP output buffering / compression if enabled:output_buffering</strong and zlib.output_compression
– check whether if you are using Cloudflare, a reverse proxy, or server cache is buffering responses
– increase server execution/request limits if needed:
– PHP max_execution_time
– PHP-FPM request_terminate_timeout
– proxy/read timeouts

So in short:

the issue is most likely not your internet speed or server hardware, but the way fpm-fcgi commonly buffers output in front of WordPress.

That is also why gpt-5.4-mini works better: it finishes faster, so it is less affected by buffering and timeout limits.

So at this point unfortunately there is not too much i can do about it but i will check more to see if i can add some kind of fallback but i think the fastest way to fix it to ask your provider to disable FastCGI / proxy buffering.

Pls let me know how it goes.