Video Production

Multiple scenes

• If Text Control is used to generate an audio file, the total number of words of all paragraphs must be greater than 200.
• If Audio Control is used to generate an audio file, the duration of each audio file must be longer than one minute.

Text control

If Text Control is used to generate an audio file, the text requirements are as follows:

• There must be fewer than 2,000 characters in each paragraph (fewer than 3,000 if SSML tags are contained).
• The total number of characters of all paragraphs in a video draft must be fewer than 300,000 if SSML tags are contained.

Video format

The supported video formats are MP4, M4V, MKV, MOV, FLV, 3GP, WMV, AVI, and WebM.

Video requirements:

• Resolution ≤ 1080p
• Frame rate ≤ 30 FPS
• AV1, VP8, VP9, H.264, or H.265 for encoding
  • VP8 and VP9 encoding is supported only for WebM videos.
  • If AV1 encoding is used for a WebM video, the video cannot be composited.
  • AV1 and H.265 are only supported by the Chrome browser.
• Video size < 1 GB
• Overlaid videos ≤ 3, including the videos configured during interaction

Audio format

The supported audio formats are MP3, M4A, and WAV.

Audio requirements:

• Only mono audios are extracted.
• The total size of audio files is less than 500 MB.

Image format

The supported image formats are PNG, JPG, and JPEG.

Image requirements:

• 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.