Avatar video captions error over 60 seconds: split the script
Inline captions on an avatar video are rejected when the estimated duration is over 60 seconds, the same cap as the job. Split long scripts into jobs.
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?
| Rule | Value |
|---|---|
Accepted estimated duration (script or video_inputs) | 4 to 60 seconds, inclusive |
| Inline captions over this | Rejected when estimated duration is above 60 seconds |
| Caption stage failure | Soft-fails: the job can still succeed with captions.status=failed |
| Billing for inline captions | No separate billed video-caption job |
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.
Sources
Related posts
More in Developers
- Azure batch takes 10,000 inputs per job; Sume sends one text per job
Azure batch synthesis accepts up to 10,000 text inputs in a 2 MB JSON body. Sume TTS 1.0 takes one transcript of up to 20,000 characters per job.
- Azure batch: 95% of outputs within 120 seconds; Sume TTS waits 30
Azure says half of batch outputs finish in 10 to 20 seconds and 95% within 120. Sume TTS sync mode waits at most 30 seconds, then hands you a status URL.
- Azure word boundaries in ms vs Sume TTS timestamps in seconds
Azure writes word timings as AudioOffset and Duration in milliseconds, in a separate file. Sume returns words[] with start and end seconds on the job result.
- Azure Long Audio API retires April 2027: long audio on Sume
Azure says the Long Audio API retires April 1, 2027 in favor of batch synthesis. Sume TTS 1.0 handles long text as async jobs capped at 1,200 seconds of audio.
Written by Sume