AtlasVoice Pro extends the AtlasVoice text-to-speech add-on for WordPress and WooCommerce. Add an audio player to posts, pages, product descriptions, and supported custom post types, including portfolios and testimonials. Visitors can listen to selected content instead of reading it on screen.

The free add-on uses the browser’s speech synthesis, so available voices and languages depend on the user’s browser and device. Pro adds server-side AI voice options, MP3 generation, and provider integrations. Install and activate the free plugin, then add AtlasVoice Pro alongside it.

Choose a voice engine

Connect a provider from the Integration menu, choose its player in Customization, then choose a voice and language in Listening.

• AtlasVoice TTS Pro: Included with Pro, with voices in 81+ languages, smart sentence splitting, and MP3 generation. This engine requires no separate API charge or third-party account.
• Google Cloud Text to Speech: Offers 300+ voices across 90+ languages, including Neural2, WaveNet, and Standard voice types. Google bills for usage.
• OpenAI Text to Speech: Offers Alloy, Echo, Fable, Nova, Onyx, and Shimmer voices, with Standard and HD models. OpenAI bills for usage.
• ElevenLabs Text to Speech: Connect the provider for its available voices and controls. ElevenLabs bills for usage.

Create and manage audio

Generate MP3 documents for individual posts or use bulk operations to process posts from the WordPress posts list. Pro can split long articles into chunks and combine them into one MP3. Visitors can download generated audio, and you can upload your own prerecorded MP3 files. Optional Google Cloud Storage backup works with all four listed TTS providers.

Control what gets read with settings for CSS selectors, excluded text, HTML tags, post IDs, categories, and tags. You can also read dynamically rendered content from the page DOM, add introductory or closing text, and include or exclude a post title and excerpt. The plugin can remove special characters, URLs, shortcodes, and HTML tags before speech generation.

Playback, languages, and analytics

Choose from six player styles and adjust presentation settings such as colors, size, margins, and show dates. Pro players include playback controls such as a progress bar, volume, speed, and download button. Audio Schema markup is available as JSON-LD for audio content.

Pro supports WPML, GTranslate, TranslatePress, and Polylang, with language detection that can adjust the voice. Read-along highlighting works at sentence level with AtlasVoice TTS Pro and OpenAI voices, and word by word with Google Cloud and ElevenLabs voices. Highlighting is off by default.

The advanced analytics dashboard includes engagement funnels, browser and device breakdowns, operating system distribution, location tracking, popular posts, peak listening hours, and listening trends. Location reporting is an optional setting.

Developer utilities and setup

Pro includes more than 50 filters and hooks and a REST API in the tta_pro/v1 namespace for programmatic audio generation.

After installing both the free plugin and Pro add-on, choose the post types where the player should appear. Connect a provider if needed, then select its player, voice, language, and style in the corresponding settings menus. Google Cloud, OpenAI, and ElevenLabs require their own provider configuration and are billed according to usage. Publish or update content to make the player available on the selected post types.