VidCraft Platforms - HeyGen and Synthesia

Deutsche Version

Back to overview

VidCraft only prepares scripts for HeyGen and Synthesia. There is no API integration: you copy the formatted script into the platform yourself and generate the video there.

Limits VidCraft checks

The validate_platform_limits tool and the pre-generation-check skill measure each scene's narration against these values:

Exceeding a limit reports FAIL; from 90 percent of the limit there is a warning. The get_platform_capabilities tool additionally returns resolution, language count and features of the platform.

HeyGen

Hard rules

• One background per scene. If the background changes, the scene is split.
• One avatar per scene.
• Text overlays are visible for the whole scene. Timed overlays belong in post-production.
• The limit of 5000 characters per scene is rarely reached: AI Studio splits long scenes itself at roughly 1000 characters. Only split manually for background or avatar changes.

Mark overlays with timing in the script like this: [post-production overlay: "Text" at 00:12-00:15]. The heygen-engineer strips these markers before formatting and lists them as post-production tasks.

Pauses

[pause 0.5s] and [pause 1s] in the script are converted by heygen_format_script into SSML <break time="0.5s"/>. Pauses only work with custom voices (voice clone, ElevenLabs, OpenAI Voice); the public HeyGen voice library ignores them. In that case the tool appends a note to the scene.

For public voices you control the pace with punctuation and paragraphs.

Variables for personalized videos

heygen_format_script automatically detects placeholders in the form {{snake_case}} in narration or on-screen text and lists them at the end of the output. All variables must be declared in the HeyGen Template API, otherwise they appear as literal text in the video. Types: text, image, video, audio, avatar. URLs go on screen only, never in the narration.

SSML prosody (optional)

Tags such as <prosody rate="slow"> and <emphasis level="strong"> are community-verified but not part of the official HeyGen documentation. They only work with custom voices, are never inserted automatically and carry a corresponding note in the output. Test them with a short scene before using them across the whole video.

Voice Director and motion prompts

For each scene the heygen-engineer recommends a Voice Director preset (Casual, Calm, Excited, Serious, Cool) or a free-form prompt. For Avatar IV avatars it adds motion prompts as short sentences such as "Points forward with confidence." You set both manually in HeyGen AI Studio.

Output format

heygen_format_script produces one block per scene with title, type (avatar, screencast, split), avatar position, background, text overlay, narration and a character counter.

Synthesia

Hard rules

• Slide-based: one scene usually maps to one slide.
• About 1000 characters per slide. Split longer text at a sentence boundary.
• Up to 150 slides per video.

Pauses

[pause Xs] is converted automatically into <break time="Xs"/> by synthesia_format_script.

Gestures and Express avatars

• Express-1: gestures via [gesture:nod], [gesture:headyes], [gesture:headno], [gesture:eyebrowsup], [gesture:increase] in the text.
• Express-2: gestures are generated automatically from context. Gesture tags are ignored. Active, concrete sentences with strong verbs produce movement; passive and abstract wording looks stiff.
• Expressive avatars react to !, ?, ... and emoticons. Passages over 60 seconds with no ! or ? look expressionless; script-reviewer, voice-checker and synthesia-engineer point this out.

Layouts

synthesia_format_script maps the visual type to a layout:

Both platforms

• The check_pronunciation tool reports pronunciation hints: years, acronyms and Latin abbreviations. It replaces nothing automatically; you decide on every suggestion.
• Record screen captures separately and upload them as background media.
• Upload logo, lower-third and colors once in the platform and reuse them across scenes.
• Voice clones are a separate, paid flow of the platforms and not part of VidCraft.