Lesson Content

What text-to-avatar video does.

Text-to-avatar video allows students to create a complete presenter video from a written script without any product URL or source footage. Write the script (or generate it with AI assistance), pick an avatar, select a voice, choose settings, and generate. The result is a fully lip-synced video of an AI presenter delivering the script.

This is the foundational creation mode for: training videos, explainer content, social media presenter clips, branded announcements, and any content where the message comes from a written script rather than a product catalog.

Script preparation.

Jogg.ai supports scripts up to 1,000 words for text-to-avatar video. Practical guidelines:

• For a 30-second video: approximately 70-80 words
• For a 60-second video: approximately 140-160 words
• For a 3-minute video: approximately 450-500 words

Write the script as natural spoken language, not written prose. Reading pace is approximately 150 words per minute for a comfortable, natural delivery. Complex or technical scripts may sound rushed if too many words are packed into a short duration.

Using the AI Script Writer.

Jogg.ai includes an AI Script Writer that can generate a script from a topic description or brief. Use it to:

• Generate a first draft when starting from zero
• Get structural suggestions for a topic you are not familiar with
• Produce multiple variations to compare before committing

Always edit the AI-generated script before using it – check accuracy, remove filler language, and ensure the tone matches your audience. The AI Script Writer integrates with ChatGPT in some versions – verify current integration status.

Voice selection.

After writing the script, select a voice from the Voice Library. The library contains thousands of voices – filter by:

• Language and accent
• Gender
• Age range
• Use case (commercial, conversational, training, narrative)

Preview selected voices with a sample of your script text before committing. A voice that sounds appropriate in isolation may not match the script's pace or tone.

Generation and review.

Select avatar, voice, aspect ratio, and target length. Generate. When rendering completes, review:

• Does the avatar's expression match the script's tone?
• Is the voiceover pace natural and clear?
• Are subtitles accurate?
• Does the total length match the intended platform?

Use ProEdit for refinements – especially voiceover speed, script corrections, and subtitle timing.