Skip to main content

Talk2U

Summary: Talk2U lets you place your product into an AI model's hands and have the model deliver a spoken script — producing a complete short-form ad video in minutes.

What is Talk2U?​

Talk2U is XSpark's core ad creation feature. Select an AI model, upload your product image, write a script, and the system generates a video of the model holding your product and speaking the lines. The result is a polished short-form ad ready for social media or marketing campaigns.

Step 1 — Select a Model​

Talk2U model and image overview

Talk2U workspace — generated videos (top) and starting images (bottom).

  1. Click Talk2U (툭투유) in the left sidebar.
  2. The workspace shows:
    • Generated Videos (생성한 동영상) — your previous Talk2U videos for this model
    • Starting Images (시작 이미지) — photos of the selected model
  3. Click the model name at the top to switch to a different model.
  4. Select one of the model's photos as your starting image, or click Create New Image to generate a new one.

The top tabs offer two editing modes after generation:

  • AI 시프트 모드 — AI automatically adjusts scenes
  • 타임라인 편집 — manual timeline editing

Step 2 — Product Synthesis (제품 합성)​

Product synthesis modal

Upload your product image and describe how to composite it.

  1. On the right panel, click 제품 합성하기.
  2. The 제품 합성 modal opens:
    • Upload product image — drag and drop or click to upload your product photo
    • 배경제거 — automatically remove the product background
    • 이미지 개수 — choose how many composite variations to generate (1 – 4)
    • 어떻게 합성할까요? — describe in text how the product should be placed (e.g., "두 이미지를 합성 후 어울리게 모델 포즈 취해줘")
  3. Click 합성하기 to generate the composite.

The composite image is placed in the model's starting image slot and is used as the base for video generation.

Step 3 — Video Generation (동영상 생성)​

Video generation modal

Enter a script and configure voice for the model.

  1. On the right panel, click 동영상 생성.
  2. The 영상 생성 modal opens:
    • 대사 — type the script the model will speak
    • 감정 표현 — toggle to add emotional expression to delivery
    • 음성 설정 — expand to select a voice tone
    • 음성 목록 — preview available voices (e.g., 톤 1) and select one
  3. Click 동영상 생성 to start rendering.

Viewing the Result​

Generated video result

Completed Talk2U video — the model holds the product and speaks the script.

  • The finished video appears in My Videos (내 비디오) and at the top of the Talk2U workspace under 생성한 동영상.
  • Click the video to play it in a lightbox viewer.
  • Use the 업로드 button to download the video file.
  • The script you entered is shown as a caption below the player.

Tips​

  • Shorter scripts (one or two sentences) produce the clearest audio sync.
  • Use the 배경제거 option for product images with complex backgrounds to get cleaner composites.
  • Generate multiple image variations (up to 4) to find the best product placement before generating the video.