HeyGen avatar script limit: 5,000 characters vs Sume's 4-60 s

HeyGen's avatar script text is limited to 5,000 characters. Sume's Avatar Video docs state no character limit; a script or multi-scene plan is accepted when Sume estimates the video at 4-60 seconds inclusive, and longer ones should be shortened or split into multiple jobs.

HeyGen figures are from its Usage Limits page; Sume figures from Avatar videos, read 2026-10-01.

What does HeyGen limit?

Usage Limits lists, under Avatar Input, script text of at most 5,000 characters and audio input of at most 10 minutes (600 seconds). Text-to-speech through POST /v3/voices/speech takes 1 to 5,000 characters and a speed multiplier from 0.5x to 2.0x.

What does Sume limit?

Duration, not characters. The docs say scripts and multi-scene plans are accepted when Sume estimates the target video duration at 4-60 seconds inclusive. You provide exactly one of script or video_inputs.

Because the check is on estimated length, a long script of short words and a shorter script of long words can land differently. The docs do not publish the estimator, so test with your own text.

Can I set a scene's length myself?

For a silence beat, yes: voice.type: "silence" requires duration and does not allow script or input_text. Spoken scenes use type: "text" with exactly one of script or input_text.

How do the limits compare?

They measure different things.

How do I size a script for Sume?

Read it aloud at your normal pace, aim inside the window, and see script length for an AI avatar video for a working rule.