AI Video Glossary
Plain-language definitions of the generative AI and video terms creators and marketers run into, from B-roll and aspect ratio to text-to-speech, lip sync and claymation.
A
A-Roll
A-roll is the primary footage that carries a video's story or message, such as the interview, presenter, or main action, with b-roll cut over it.
Read definitionVideo ProductionAspect Ratio
Aspect ratio is the proportion of a video's width to its height, written as W:H, such as 16:9 for YouTube or 9:16 for TikTok, Reels, and Shorts.
Read definitionB
C
F
Faceless YouTube Channel
What is a faceless YouTube channel? It is a channel where the creator never appears on camera, relying on voiceover, B-roll, animation, or screen recordings.
Read definitionVideo ProductionFrame Rate
Frame rate is how many still images (frames) a video shows per second, measured in fps. 24 fps looks cinematic, 30 fps is standard, 60 fps looks smooth.
Read definitionH
L
N
S
T
Talking Head Video
What is a talking head video? A video where a person speaks directly to the camera, usually framed from the chest or shoulders up.
Read definitionAI VideoText-to-Speech (TTS)
Text-to-speech (TTS) is technology that converts written text into spoken audio using a synthetic voice, often used for video voiceovers.
Read definitionU
V
Video Resolution
Video resolution is the number of pixels in each frame, written as width x height, such as 1920 x 1080 for 1080p or 3840 x 2160 for 4K.
Read definitionAI VideoVoice Cloning
Voice cloning is the use of AI to create a synthetic copy of a real person's voice that can then say any new text in that voice.
Read definition