HeyGen avatar script limit: 5,000 characters vs Sume's 4-60 s
HeyGen caps avatar script text at 5,000 characters. Sume has no character cap in its docs: it accepts scripts estimated at 4-60 seconds inclusive.
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 The docs do not publish the estimator, so test with your own text.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.
| Item | HeyGen | Sume |
|---|---|---|
| Script cap | 5,000 characters | None in characters |
| Length gate | Audio input up to 10 minutes | Estimated 4-60 seconds inclusive |
| When over | Not stated on the page | Shorten or split into multiple jobs |
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.
Sources
Related posts
More in Developers
- HeyGen do_not_translate_terms vs Sume: handle terms before speech
HeyGen brand glossaries now take do_not_translate_terms and forced_translations for video translation. Sume has no glossary field; handle terms in your text.
- HeyGen brand glossary: speech changes, captions keep spelling
HeyGen's brand_glossary_id changes synthesized speech only; captions keep the original spelling. Sume has TTS pronunciation_dict_id and a caption stage.
- HeyGen brand kit from a website URL vs Sume product and scene
HeyGen builds a stored brand kit from a website URL with POST /v3/brand-kits. Sume has no kit object: you pass product, scene and avatar inputs per request.
- HeyGen download_failed error: URL rules vs Sume's media errors
HeyGen download_failed means a media URL was not public, mismatched or corrupt. Sume returns image_not_fetchable or input_media_unreachable for similar cases.
Written by Sume