Description

QuikVox AI is a powerful WordPress assistant designed to streamline your podcast production workflow. By leveraging the advanced capabilities of Google Gemini AI, it allows you to generate high-quality scripts from your existing content and convert them into natural-sounding audio—all without leaving your WordPress dashboard.

Whether you are an AI news blogger or a content creator looking to expand into audio, QuikVox AI provides the tools to automate the tedious parts of scriptwriting and voice generation.

Key Features

AI-Powered Script Generation: Automatically extract content from your posts/pages and generate professional podcast scripts using Google Gemini (Flash/Pro/Flash-Lite models).
Natural AI Voices: Convert scripts into audio using the latest Gemini 2.5 TTS (Generative Audio) models. Choose from 15+ high-quality voices with distinct characteristics.
Multilingual Support: Generate content in 5 major languages: Japanese, English, Chinese (Simplified/Traditional), and Korean.
Prompt Management: Save and manage custom prompt sets for different podcast styles. Includes an AI translation tool to help you expand your prompts globally.
Seamless Media Integration: Generated audio files are automatically saved to your WordPress Media Library and can be embedded directly into your articles via a simple audio player.
Post & Page Support: Works with both standard Posts and Pages, allowing you to turn any content into audio.

Advanced Voice Selection

Unlike basic TTS plugins, QuikVox AI provides detailed metadata for each voice:
* Gender Identification: Clear male/female labels.
* Tone Characteristics: Voices are tagged with their unique style (e.g., “Warm, deep, informative” or “Soft, narrating”).
* Dynamic UI: The editor dropdown shows icons and descriptions so you can find the perfect voice for your persona.

External Services

This plugin connects to an external service:

Google Gemini API

– Purpose: Generate podcast scripts from post content, convert text to speech, and fetch the available model list in the settings screen when a Script Generation API key is saved.
– Data sent: Post content, optional user prompts, and the API key required to query Google’s models endpoint for the settings screen model list
– Service provider: Google
– Privacy Policy: https://policies.google.com/privacy
– Terms of Service: https://policies.google.com/terms

Users must provide their own API key to use this feature. No data is sent to external services without user action (clicking “Generate Script” or “Generate Voice”).
The settings page may also contact Google’s models endpoint to populate the model selector when a saved API key is present.

Installation

Upload the quikvox-ai folder to the /wp-content/plugins/ directory.
Activate the plugin through the ‘Plugins’ menu in WordPress.
Navigate to Settings > QuikVox AI to enter your Google Gemini API Key.
Optionally, configure Your Voice Generation API Key to enable TTS.
Start creating by clicking “Create Podcast Script” in the sidebar of any Post or Page editor.

FAQ

Where do I get a Gemini API Key?: You can obtain an API key from the Google AI Studio.
Are the audio files hosted locally?: Yes, generated audio files (WAV format) are saved directly into your wp-content/uploads directory and registered in your Media Library for full ownership.
Does it support multi-speaker podcasts?: In the current version (v0.7.7), it supports single-speaker script generation. Multi-speaker support (dialogue) is planned for the Pro version (v0.9+).

Reviews

There are no reviews for this plugin.

Contributors & Developers

“QuikVox AI” is open source software. The following people have contributed to this plugin.

takeshiue

Translate “QuikVox AI” into your language.

Interested in development?

Browse the code, check out the SVN repository, or subscribe to the development log by RSS.

Changelog

0.8.2

Moved the admin page from a top-level menu into the WordPress Settings menu using add_options_page().
Kept the existing capability and admin page slug unchanged to preserve access behavior.
Normalized line endings across plugin source files to LF for Plugin Check compatibility.
Cleaned the release packaging scope so development-only files are excluded from the WordPress.org package.

0.8.1

Review hardening: moved admin request parsing out of the settings page renderer so Prompt Sets state changes stay in dedicated handlers with nonce and capability checks.
Prompt Sets admin view now uses sanitized controller state passed from the admin class instead of reading request values directly in the template.

0.8.0

Security hardening: added whitelist validation for model_id and tts_model_id POST parameters.
Security hardening: added enum validation for prompt_lang and speaker_type inputs.
Fixed output escaping: applied esc_url() when inserting audio URL into HTML attribute.
Fixed undefined variable: initialized $json_text before conditional block in ajax_translate_prompt().
Fixed API error message: sanitize_text_field() applied to Gemini error response before output.
Fixed asset versioning: replaced time() with PODCASTMAKER_VERSION in enqueue_editor_assets().
Fixed nonce order: check_admin_referer() now called before current_user_can() in handle_create_default_prompt_set().
Fixed superglobal hygiene: replaced $_REQUEST with $_POST for state-changing ID parameter.
Fixed wp_json_encode(): replaced native json_encode() calls in Gemini API class.

0.7.9

Fixed all WordPress Plugin Check errors (0 errors, 0 warnings).
Unified $wpdb->prepare() usage with spread operator across usage-tracker.
Added phpcs:ignore annotations for legitimate direct DB queries.
Normalized line endings to LF across all PHP files.

0.7.8

Renamed plugin to QuikVox AI (slug: quikvox-ai).
Migrated all inline scripts/styles to wp_enqueue (admin.js / admin.css).
Fixed i18n: text domain unified to quikvox-ai and missing 2nd args added.
Added ABSPATH guards to all PHP files.

0.7.7

Code consistency improvements for WordPress.org standards.

0.7.6

WordPress.org submission preparation.
Removed ElevenLabs API integration (Gemini TTS only).
Added External Services disclosure section.
Security improvements: Enhanced nonce verification and data sanitization.
Code cleanup for WordPress.org compliance.

0.7.5

Official preparation for WordPress.org directory submission.
Updated Gemini 2.5 TTS (GA) model support.
Added support for Gemini 1.5 Flash-Lite.
Enhanced Voice metadata (Name, Gender, Characteristics) in UI.
Improved buttons: Scripts can now be embedded directly under the player.
General UI/UX polishing for the admin settings page.

0.5.0

Initial beta release with basic script generation and TTS support.