DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///DROPGoogle launches Gemini 3.8 Flash TTS and Flash-Lite TTS///DROPGemini Omni brings 1080p generation to Google Vids///BREAKClaude Opus 5.5 is here: 1M context, $4 input / $20 output///BREAKOpenAI adds GPT-6 Sol and Luna to the GPT-6 family///PAPEROpus 5.5's system card documents gains—and evaluation limits///BREAKGrok 4.7 launches at $2 input / $6 output per million tokens///DROPGrok Voice Transcribe 2.0 targets difficult real-world audio///TRENDGoogle steers new Gemini API projects to 3.8 Flash or 3.5 Flash-Lite///
DARC.DEV

[ 04 — Maker · 6 lessons · ~3.5h with exercises ]

AI Creator Studio

Use image, video and voice tools in a repeatable production workflow. Learn to control references, continuity, consent, asset provenance and publishable quality.

← All learning paths

Your progress

0/6

Mark completion after doing the exercise. The checklist records your self-assessment, not a certificate. Stored for this browser only.

Module 01

A brief you can actually use

Capture intent without inventing requirements.

~30 min · read + exercise

From voice note to product brief

Separate decisions, suggestions and open questions.

Exercise

Use your own short recording or written notes to create an evidence-backed brief.

Done when: Every commitment is supported by the source or marked for a decision.

Read the lesson

~25 min · read + exercise

Choose the correct media interface

Distinguish text, live dialogue, TTS and restricted variants.

Exercise

Map three desired outputs to the correct interface and billing unit.

Done when: A voice workflow does not accidentally depend on a text-only output model.

Read the lesson

Module 02

Produce with constraints

Make images and shots serve a coherent story.

~40 min · read + exercise

Review generated images

Apply a visual brief and rights review.

Exercise

Evaluate three candidate images against composition, typography and mobile-crop requirements.

Done when: Selection is based on delivery criteria, not thumbnail impact alone.

Read the lesson

~45 min · read + exercise

Plan a coherent video stack

Budget usable shots and editing work.

Exercise

Create a shot plan with reference assets and continuity constraints.

Done when: The plan counts retries and specifies what a usable shot means.

Read the lesson

Module 03

Voice and publishing

Verify what users hear and what you claim.

~40 min · read + exercise

Evaluate narration and conversation

Check numbers, corrections, timing and rights.

Exercise

Prepare five audio test cases and a consent/retention note.

Done when: A fluent but incorrect answer is labeled as a failure.

Read the lesson

~30 min · read + exercise

Keep a source and asset trail

Make the final piece inspectable.

Exercise

Attach source URLs, checked dates, asset origins and synthetic-media labels to the project.

Done when: Another person can verify the important factual claims and asset permissions.

Read the lesson