AkaVoice is a WordPress plugin that auto-converts blog articles into podcasts on Spotify, Apple Podcasts, and Amazon Music. See features, pricing, and how it…
Freemium with one-time credit packs. Free tier includes 3 podcasts with no credit card. Paid credits never expire and require no subscription: Small EUR 3 (100 credits), Medium EUR 30 (1,000), Large EUR 275 (10,000), XL EUR 2,500 (100,000). Bring-your-own-key means you also pay your own AI/TTS provider costs (about EUR 0.05 per podcast with Azure TTS).
AkaVoice is a WordPress plugin from Akasearch S.r.l. (Rome, Italy) that automatically converts your existing blog articles into professionally produced podcast episodes. Rather than reading text robotically, its AI first rewrites each article into a radio-friendly script, stripping out tables, links, and unpronounceable acronyms, then generates natural-sounding audio using text-to-speech and distributes the finished episode to Spotify, Apple Podcasts, Amazon Music, and other directories through a built-in Spreaker integration. The plugin runs on a bring-your-own-key model: you connect your own OpenAI, Azure, or Google API credentials (encrypted with AES-256-CBC in your WordPress database and never stored on Akasearch servers), which keeps per-episode costs low (around EUR 0.05 per podcast with Azure TTS). AkaVoice scans your site on a schedule, queues articles that have not yet been converted, prioritizes them using Google Search Console traffic data, embeds an audio player back into each post, and keeps your podcast RSS feed updated automatically. It offers more than 15 AI voices across Italian, English, Spanish, French, German, Chinese, and Russian, and produced over 71,000 podcasts during its beta program. A free tier lets you create 3 podcasts with no credit card, and paid credit packs (which never expire) scale from small blogs to enterprise publishers.
Key Features
Automatic article-to-podcast conversion — Scans your WordPress site on a schedule (roughly every 4 minutes), queues articles that have not yet been converted, and prioritizes them using Google Search Console traffic data.
AI radio-style rewriting — Rewrites each article into a professional radio-friendly script, removing tables, links, and unpronounceable acronyms so the audio sounds natural rather than robotic.
15+ AI voices in 7 languages — Offers more than 15 text-to-speech voices (e.g. Azure Neural, OpenAI, and Google Neural2) across Italian, English, Spanish, French, German, Chinese, and Russian.
Multi-platform podcast distribution — Publishes finished episodes to Spotify, Apple Podcasts, Amazon Music, iHeart, Deezer, Castbox, and Podchaser through a built-in Spreaker integration, and keeps the podcast RSS feed updated.
Embedded audio player — Automatically embeds an audio player into each converted article so readers can listen inline.
Bring-your-own-key model — Connect your own OpenAI, Azure, or Google API credentials, encrypted with AES-256-CBC in your WordPress database and never stored on Akasearch servers, keeping per-episode costs around EUR 0.05 with Azure TTS.
Pros & Cons
Pros
Fully automated pipeline: scans your WordPress site, rewrites articles into radio-style scripts, generates audio, and publishes episodes without manual work.
One-click distribution to Spotify, Apple Podcasts, Amazon Music, and other directories via built-in Spreaker integration.
Bring-your-own-key model keeps per-episode costs very low (about EUR 0.05 with Azure TTS) and keeps your API credentials encrypted in your own database.
Credit-pack pricing with no monthly subscription and credits that never expire.
More than 15 AI voices across seven languages, plus a free tier of 3 podcasts with no credit card required.
Cons
Requires your own OpenAI, Azure, or Google API keys, plus a free Spreaker account, so setup involves more moving parts than a fully hosted service.
Works only inside WordPress (5.8+ / PHP 7.4+), so it is not an option for sites on other CMS platforms.
AI-rewritten and text-to-speech audio may still need review for niche or highly technical content to ensure accuracy and tone.