Video Production

Video script

• A video script can contain a maximum of 100 scenes.
• A video script can contain only one virtual avatar image model and one voice model.

Text control

• A maximum of 10,000 characters are allowed in each scene.
• A maximum of 100,000 characters are allowed in all scenes.
• If a single scene contains Speech Synthesis Markup Language (SSML) tags, the text size must be less than 128 KB.

Speech control

Audio files uploaded in a single scene cannot be larger than 100 MB.

Video format

You can insert MP4, M4V, MKV, MOV, FLV, 3GP, WMV, AVI, and WebM videos.

Note: On the video production page, if an FLV, 3GP, WMV, or AVI video is inserted, you cannot preview the video and can see only a preview image of the video. This is due to browser incompatibility. However, after video compositing, the inserted video can play seamlessly with the main video.

Requirements on an inserted video:

• Resolution ≤ 1080p
• Frame rate ≤ 30 FPS
• AV1, VP8, VP9, H.264, or H.265 encoding
  • Only WebM videos support VP8 and VP9 encoding.
  • If a WebM video uses AV1 encoding, the video cannot be composited.
  • Only the Chrome browser supports AV1 and H.265 encoding.
• Video size < 1 GB
• A maximum of two video overlays

Precautions of video upload:

• An uploaded video overlay cannot be modified. You can modify it only on your local device and then upload the new one to the console.
• The aspect ratio of a video overlay is locked. You can adjust its width and height only on your local device and then import the new one.
• A video overlay cannot exceed 30 minutes.

Audio format

You can insert MP3, M4A, and WAV audios.

Requirements on an inserted audio:

• Only mono audios can be extracted.
• The audio size should be less than 500 MB.

Image format

You can insert PNG, JPG, or JPEG images.

Requirements on an inserted image:

• Resolution ≤ 1080p
• Image size < 500 MB

Subtitling

Punctuation marks (such as ,.:;!?...) in subtitles will be automatically removed.

• If the punctuation mark to be automatically removed is in the middle of a piece of text, a space is added after the punctuation mark is removed.
• If the punctuation mark to be automatically removed is at the end of a paragraph, it will be removed directly.

Some punctuation marks (""()·~--) cannot be automatically removed.

Video production task

• Retention duration: Historical tasks can be retained for six months. After that, the tasks are not displayed on the Video Production page of Task Center on the console.
• Queue limit: A maximum of 20 tasks can be queued at the same time.
• Concurrency limit: A maximum of 20 videos can be composited at the same time.

PowerPoint file

Constraints:

• You can upload a PowerPoint file of no more than 100 slides.
• If the font of the PowerPoint file cannot be displayed on the MetaStudio console, convert the PowerPoint file to a PDF file before importing it.

  For details, see How Do I Convert a PowerPoint File to a PDF File?

• A PowerPoint file containing special effects such as animation cannot be displayed on the MetaStudio console. You are advised to export the PowerPoint file as a video and then import it.

  See How Do I Present the Animation of a PowerPoint File?

• If a PowerPoint file fails the parsing and cannot be uploaded, rectify the fault by referring to What If a PowerPoint File Cannot Be Uploaded Due to a Parsing Failure?