Avatar video captions error over 60 seconds: split the script

The error appears because Sume rejects an avatar request with inline captions when its estimated duration is above 60 seconds. The avatar job itself is limited to 4 to 60 seconds, so a long product pitch has to be split into several jobs, each with its own script.

HeyGen's updates page, read 2026-10-01, lists BrandKit and Video Podcast updates; it says nothing about caption limits. The limit below is Sume's, from Avatar videos.

Which limits apply?

How do I split a long pitch?

Cut the script at sentence or scene boundaries so each part lands under 60 seconds, then send each part as its own POST /v1/avatar-1.0/talking-video request with the same avatar_handle. The docs say to shorten longer scripts or split them into multiple jobs. Join the finished clips afterwards; the longer than 60 seconds guide covers the stitching step.

Can I caption the long video another way?

Yes. Standalone Video captions work on an existing public video URL, separate from the avatar job, and see add captions to a long video. Inline captions are meant for the single avatar render.

Does language change the caption style?

No. The captions page says language never selects the style or the font; it is only a speech-to-text hint. A Korean script with style: "slam", punch or tiktok-green is rejected with 400 caption_hangul_text_latin_style, so name a Hangul style for Korean speech.