WP Listen

WP Listen enhances your website’s accessibility and engagement by converting written content into natural, human-like audio using the powerful ElevenLabs Text-To-Speech API. With a sleek floating play button available on blog posts, visitors can instantly listen to your content on the go—improving user experience, increasing time on page, and making your site more inclusive for all audiences.

Installation

• Install the WP Listen plugin & activate it.
• There will be a new “WP Listen” menu created in the WordPress panel.

API Log

Here, you can view the API Report. It will show you the total API requests made from your website, along with the total characters sent in the API request to be converted into an audio, and also the average API requests made per day.

Maintenance

Here, you can execute certain tasks as follows:

• Delete API Log Data
  If this task is executed, the API reports data will be deleted, and the table will be empty on the “API Log” sub-menu

Options

Text-to-Speech

In this tab, you need to provide the API key to connect your site to ElevenLabs. You also need to provide the configuration settings for the voice in which the text will be converted.

1. API Key
   Here, you need to provide the API key to connect your site to ElevenLabs. Make sure the key is from a paid account of ElevenLabs; otherwise, the text-to-speech feature will not work on the frontend pages when someone tries to convert the page’s text to speech. Also, make sure to provide access to all the features when creating an API key on the ElevenLabs site.
2. Voice
   Once the API from a paid account is provided, click the “Refresh Voices” button to fetch all the voices from your respective ElevenLabs account. The voice selected will be the voice in which the text will be converted for the user to listen.
3. Voices Available on Frontend
   Select which voices should be available in the frontend player (floating button and shortcode). If you leave this empty, all voices will be available.
4. Allow Visitors to Change Voice
   If unchecked, visitors will not see the voices dropdown, and the default admin-selected voice will be used.
5. Or Enter Voice ID Manually
   If you do not want to use the dropdown and fetch the voice from your respective ElevenLabs account using the voice’s ID, you can use this option. The respective voice will be fetched directly in the “Voice” option.
6. Optimize Streaming Latency
   Here, you can optimize the text-to-speech latency of the voice. You can turn on latency optimizations at some cost of quality. The best possible final latency varies by model. 
   You can select from the following options:

• Default mode (no latency optimizations) 
• Normal Latency 
• Low latency 
• Very low latency 
• Ultra low latency

7. Stability
   Here, you can set the stability slider. It determines how stable the voice is and the randomness between each generation. Lower values introduce a broader emotional range for the voice. Higher values can result in a monotonous voice with limited emotion.
8. Similarity Boost
   Here, you can set the Similarity Boost slider. It determines how closely the AI should adhere to the original voice when attempting to replicate it.
9. Style
   Here, you can set the Style slider. It determines the style exaggeration of the voice. This setting attempts to amplify the style of the original speaker. It does consume additional computational resources and might increase latency if set to anything other than 0.
10. Use Speaker Boost
    This setting boosts the similarity to the original speaker. Using this setting requires a slightly higher computational load, which in turn increases latency.

Style

Here, you can set the icon’s position, size, and color-related settings on the respective pages on which it will be visible.

1. Bottom Right
   Here, you can select the position of the floating button.
2. Button Color
   Here, you can select the background color of the floating button.
3. Icon Color
   Here, you can select the color of the icon inside the floating button.
4. Button Size
   Here, you can enter the size of the floating button in pixels (40-100).

Misc

Here, you can set the Miscellaneous settings of the addon.

1. Post Types
   Here, you can select the post types where the text-to-speech player will be available.
2. Disable Floating Button
   When enabled, the floating button will not appear anywhere. You can still use the shortcode to embed the audio player where needed.
3. Speech Text Before
   Here, you can enter the text to speak at the beginning of the audio file.
4. Speech Text After
   Here, you can enter the text to speak at the end of the audio file.
5. Read Title
   Here, you can select whether to read the title of the page before the page content.
6. Shortcode (Current Post)
   Use this shortcode in a post/page to embed the audio player for that specific post.
7. Shortcode (Specific Post)
   Use this shortcode in a post/page to embed the audio player for any specific post. Replace “123” with the actual post ID you want to embed the audio player for.

Here is how the Text-To-Speech Icon will look on the frontend pages:

---

FAQ’s

1- Is it necessary to have any plugin activated to use this plugin?

It is not necessary to have any plugin activated to use this plugin.

2- Can I select the position where I want to display the text-to-speech icon on my site?  

You can select the position where you want to display the text-to-speech icon on my site using the “Position” option.

3- Can I change the icon colors to match my theme?

You can match the icon colors to your theme using the “Button Color” and “Icon Color” options, respectively.

4- Can I select on which respective pages I want the text-to-speech icon to display?  

You can select on which respective pages you want the text-to-speech icon to display using the “Post Types” option.

5- Can I provide any text before or after the page content is read?  

You can provide any text before or after the page content to be read using the “Speech Text Before” and “Speech Text After” options.

6- Is there any limit to how many characters/words should be on the respective page for the text-to-speech functionality to work properly?  

It is recommended that your word count on the respective page should not be more than 10,000 words.

Changelogs

1.0.0

• Initial Release.