Sahajanand Post to Speech

Sahajanand Post to Speech helps you convert WordPress posts into listenable audio. Add the Sahajanand Post To Speech block, generate speech from your post content, and visitors get a simple audio player — no post text is shown on the frontend.

Features

• Gutenberg block for post-to-audio conversion
• Post content or custom text as the audio source
• Frontend shows only the audio player (no duplicated post text)
• Browser (WASM) or external API generation modes
• 8 built-in voices with adjustable speed
• Generated audio saved to the WordPress media library

Generation modes

• Browser (WASM) — runs in the block editor using ONNX Runtime Web. No server-side TTS engine required. Speech models are downloaded on first use.
• API — proxies requests to a compatible HTTP TTS API you host. Useful for long posts or low-powered devices. Your API key stays on the server.

Credits

This plugin uses the open-source KittenTTS speech synthesis models from KittenML and bundles eSpeak-NG (GPL-3.0-or-later) for browser phonemization.

Sahajanand Post to Speech is developed independently and is not affiliated with, endorsed by, or sponsored by KittenML.

External services

This plugin may contact the following third-party services when generating audio:

Browser mode (editor only)

• Hugging Face — downloads speech model files configured in settings (default models published by KittenML). ONNX Runtime and eSpeak-NG WASM files ship inside the plugin package.

API mode (server-side, when configured)

• Your configured TTS API URL — WordPress sends post text and receives WAV audio. Only the site administrator configures this URL and API key.

No data is sent to external services on the public frontend unless you use API mode during generation in the editor.