Glossary
The words behind the work.
Making video without a camera comes with its own vocabulary. Here are the 30 terms you'll meet most, explained in plain language with no jargon and no fine print.
People on screen
- AI avatar
- A digital presenter that can speak on screen without a camera or a film crew. You give it a face and words, and it delivers them as video.
- AI talking head
- A video of a person speaking straight to the viewer, made from a single photo and a script instead of a live recording. It is the most common way to put a face to your message fast.
- Twin
- Your saved combination of a photo, a voice, and your consent to use them. Once a Twin is ready, you can reuse it for any video without setting things up again.
- AI presenter
- A virtual person who reads your script to camera, built from a photo and a voice instead of a hired host. Your Twin is your own AI presenter, so the same face and voice carry across every video.
- AI spokesperson
- A consistent on-screen face that represents a brand or message across many videos. Because it is built from your own consented Twin, you control the likeness and never depend on a model's schedule.
- Digital human
- A realistic computer-made person who can look at the camera and speak. In Studio, your digital human is your Twin: a likeness you have given permission to use.
- AI UGC ad
- A short, casual-looking ad in the style of a real customer review, made with an AI presenter rather than a filmed creator. It pairs the trust of user-generated content with the speed of a single Render.
Voice and sound
- Voice cloning
- Making a digital copy of a specific voice from a short sample, so it can read any new script in that same tone. You use it to keep one consistent voice across all your videos.
- Voiceover / text-to-speech
- Turning written words into spoken audio. You can use a ready-made voice or your own cloned voice, with no recording booth required.
- Lip sync
- Matching a presenter's mouth movements to the words being spoken, so the talking looks natural. Good lip sync is what makes a face on screen feel real instead of dubbed.
- AI dubbing
- Replacing the spoken track of a video with a new voice, often in another language, while keeping the timing tight. It lets one Render reach audiences who speak differently from you.
- Voice library / stock voices
- A collection of ready-made voices you can pick from when you would rather not clone your own. You choose a tone that fits the message and start your Render right away.
Footage and motion
- B-roll
- Extra supporting footage that plays over narration, like a product close-up or a city street. It keeps a video visually interesting when no one is talking on screen.
- Image-to-motion
- Turning a still picture into a short moving clip, adding gentle motion like a slow zoom or a turning head. It brings a single image to life without filming anything.
- UGC video
- Short, casual clips that look like a real person talking on their phone, the style people trust in product reviews and ads. UGC stands for user-generated content.
- Product photography (AI)
- Studio-style product images created without a photo shoot, set against clean or styled backgrounds. You use them for shops, ads, and social posts.
- Faceless video
- A video that tells its story with footage, captions, and a voiceover instead of a person on camera. It is a good fit when you want to stay off screen but still publish often.
Making and output
- Storyboard / script
- The written plan for your video: what is said and, sometimes, what is shown for each part. A clear script is the fastest path to a clip that lands.
- Render
- Both the act of turning your photo, voice, and script into a finished video, and the finished video itself. You pay for each Render you make.
- AI video generator
- A tool that builds finished video from simple inputs like a photo, a voice, and words. Studio is an AI video generator with sensible defaults, so you get a clip without learning a timeline.
- Text-to-video
- Turning written words straight into moving video, where your script drives both what is said and what is shown. It is the fastest route from an idea to a Render.
- AI video editor
- Software that assembles and adjusts clips for you instead of asking you to drag pieces around by hand. Studio leans on smart defaults so a polished Render takes minutes, not an afternoon.
- Aspect ratio
- The shape of your video frame, such as tall for phone feeds or wide for websites and presentations. Picking the right one keeps your video looking right wherever it plays.
Trust and disclosure
- AI disclosure
- Letting viewers know a video was made with AI, which is increasingly required by law in many places. Every Render ships ready to meet these expectations.
- Content Credentials (C2PA)
- A tamper-evident label attached to a file that records how it was made. It is an open industry standard that helps prove where a video came from.
- Synthetic media
- Any image, audio, or video that is generated or altered by software rather than captured in full by a camera or microphone. Every Render is synthetic media, made from your own inputs and labeled as AI-made.
- Deepfake
- A face or voice swapped onto someone without their permission, usually to deceive. A Twin is the opposite: it only uses a likeness you have consented to, and every Render is clearly disclosed as AI, so it informs rather than tricks.
- Consent-first AI
- Building only from faces and voices that the rightful person has agreed to use. It is how Studio works by design, since a Twin cannot be made without recorded consent.
- Likeness rights
- A person's say over how their own face and voice are used. We keep these rights with you: your Twin is yours, and we do not reuse your likeness for anyone else.
- Invisible watermark
- A hidden marker woven into a file that survives sharing and reposting, used to trace where a video originated. It works alongside visible labels and Content Credentials to keep each Render accountable.
Now make your own.
You've got the vocabulary. Put it to work with a free trial: one full minute on us, no credit card required.