HeyGen feature that turns documents or links into a two-host video podcast with AI avatars.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
HeyGen Video Podcasts is a feature within HeyGen's AI video platform that converts source material, such as documents, papers or links, into a short podcast-style video with two AI hosts discussing the content. It is comparable to a video version of NotebookLM's audio overviews. A reviewer (Matt Wolfe) generated a 2:40 episode from the AlphaEvolve paper, while also voicing concern about the low-quality content such tools can produce at scale.
The feature sits alongside HeyGen's other tools: avatar generation (Avatar III, IV and V), voice cloning, text-, image- and audio-to-video, translation with lip-sync in 175+ languages, and an editor for refining scripts and visuals. Details specific to the podcast feature (length limits, credit cost, customization) were not in the provided material.
It is accessed through HeyGen's web app and is bundled with HeyGen's plans. The Free plan allows 3 watermarked videos per month of up to 1 minute; paid tiers start at Creator ($29/mo) and go up to Business ($149/mo) and Enterprise. Which plans include the podcast feature was not confirmed.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
A feature that turns documents or links into a two-host video show, like a video version of NotebookLM. The creator generated a 2:40 podcast on the AlphaEvolve paper, but is not a fan of the AI slop it enables.
Closest neighbours by meaning, not just by category.
App · HeyGen
AI video platform for creating avatar-led videos from text, with voice cloning and lip-synced translation in 175+ languages.
App · Amazon
Alexa+ feature that generates on-demand, podcast-style audio episodes on a chosen topic.
Model · Meituan
Open-weights audio-driven avatar video model from Meituan, built on LongCat-Video, with 8-step distilled inference.
Model · ByteDance
ByteDance image-and-audio-driven digital human video model, offered through the BytePlus API.
App
Open-source, self-hostable alternative to Google NotebookLM with multi-provider AI, local models and multi-speaker podcasts.
Model · Hao AI Lab
Open-weight 4-step sparse-distilled version of MiniMax H3 for fast text-to-video-and-audio generation on Blackwell GPUs.
