Sume Avatar 1.0
Sume Avatar 1.0 by API: reusable avatars, talking video from a script, multi-scene and two-speaker videos, previews, B-roll, and Face Swap (Beta).
Start with Introducing Sume Avatar 1.0
How do AI avatars work? Face, voice, and video, step by step
An AI avatar video is assembled from parts: a face, a voice to match it, and motion that makes the face say your script. How each step works on Sume.
What is AI UGC? Meaning, how it's made, and how it differs
AI UGC is UGC-style video made with AI: a generated presenter speaks your script to camera, the way a creator would on a phone. How it differs.
What is a talking head video? Meaning and how to make one
A talking head video shows one person speaking to the camera, framed from about the chest up. What it means, what it's for, and how AI makes one.
Talking head vs B-roll: what's the difference?
A talking head is the shot of someone speaking to camera; B-roll is the footage you cut to while their voice keeps playing. How the two fit together.
Difference between lip sync and dubbing: which do you need?
Dubbing replaces the speech in a video; lip sync matches a mouth to the audio. Lip-sync dubbing does both. What each means, and which one you need.
AI avatar vs AI agent: what's the difference?
An AI avatar is a face and a voice that present content; an AI agent is software that plans steps and uses tools. How they differ, and how they meet.
UGC video prompt for AI avatars: what goes in each field
A UGC video prompt for an AI avatar is three inputs, not one: the creator's words, a scene prompt for the setting and light, and a product image.
AI avatar prompts: how to describe a talking presenter
An AI avatar prompt for video describes one person: age, look, hair, clothing, and expression. What to write, what Sume adds, and what it can't set.
AI avatar video editing: what you can change after rendering
AI avatar video editing: trims, captions, music, B-roll, and joins work on the finished MP4; new words, a new voice, or a new look need a re-render.
How to make a photo talk with AI: voice, then lip sync
Make a photo talk in two steps: turn your text into speech, then lip sync the photo to that audio. On Sume: TTS 1.0, then VEED Fabric 1.0.
How to clone yourself with AI: your face and your voice
To clone yourself with AI, pair a photo of your face with a clone of your voice. On Sume: clone the voice, speak with TTS 1.0, lip sync with Fabric.
AI avatar language: which languages can an avatar speak?
Sume's Avatar 1.0 talking video speaks English only today. For Spanish, Hindi, or Korean, make the speech with TTS 1.0, then lip sync it.
Lip sync AI translate: how to dub an avatar video
Sume can't re-sync lips in existing footage. To dub an avatar video, translate the script, speak it with TTS 1.0, and lip sync the face with Fabric.
AI avatar with emotions: set tone and speaking speed
Avatar 1.0 talking videos have no emotion or speed setting. Set emotion, speed, and volume on TTS 1.0 speech, then lip sync the avatar with Fabric.
AI avatar with hand gestures: make an avatar move or dance
Avatar 1.0 videos have no gesture setting. To pick hand gestures or dance moves, drive the avatar with a clip of up to 30 seconds via motion control.
Script for an AI avatar: how many words fit in 60 seconds
An AI avatar script is the words the avatar speaks. Sume's estimator today counts 2.8 words per second, so 60 seconds holds roughly 165 words.
UGC ad script for AI avatar videos: hook, demo, CTA
A UGC ad script is a hook, the product in use, and a call to action. For a Sume avatar, write each beat as a scene in a video of up to 60 seconds.
Talking head video background music: a bed under the voice
Keep background music well under the voice. A Sume avatar video preview can carry a soundtrack at volume 0.05 to 0.4; Timeline adds fades and ducking.
Talking head video format: aspect ratio, size, and file
A talking head video's format follows where it plays: vertical, 16:9, square, or 4:5. Sume avatar videos come in five ratios as MP4 at 720p.
Face swap a video with a photo: create an avatar first
Sume's Face Swap (Beta) takes a ready avatar, not a photo. Turn the photo into an avatar first, then swap it onto a 4–15 second public video.
Real estate agent AI video: one avatar for every listing
Real estate agents can make AI videos without filming: create an avatar from a photo once, then script each video with a listing photo as the scene.
API for AI avatar talking-head videos from a script: how to choose
How to choose an API for AI avatar talking-head videos from a script: HeyGen, Synthesia, Argil, Creatify and Sume compared on price unit, engines and limits.
How to make an AI avatar video longer than 60 seconds
One Sume avatar video job covers an estimated 4-60 seconds. Split the script, render each part, and join the parts with Timeline 1.0 for a longer video.
Add B-roll to a talking-head avatar video with the Sume API
Keep an Avatar 1.0 clip's voice as one Timeline spine, cut away to B-roll slots, and cut back with source_in equal to start so the lips stay on the words.
AI avatar conversation video API: two speakers in one dialogue
A Sume avatar video job resolves one avatar, so a two-person dialogue is one job per turn, cut together in speaking order with Timeline 1.0.
AI avatar video with your product and background via API
Add product_image and a scene prompt or photo to a Sume Avatar 1.0 talking video, then check the first frame in a preview before the full render.
Stock AI avatars API: find a ready-made avatar for a talking video
Search Sume's avatar catalog with POST /v1/avatar-catalog/search, pick a ready public avatar, and pass its handle to a talking video without creating one.
How to create a reusable AI avatar with the Sume Avatar 1.0 API
Send POST /v1/avatar-1.0/generate with an avatar_handle and a prompt, profile, or image input. Poll the job, then reuse the handle for avatar videos.
Talking avatar video API: generate an avatar video from a script
POST /v1/avatar-1.0/talking-video turns a ready avatar and a 4-60 second script into a talking video. Options, captions, polling, and per-second rates.
Multi-scene avatar video API: build one video from ordered scenes
Send ordered video_inputs instead of one script to compose spoken and silent scenes into one 4-60 second avatar video. Scene fields, rules, and limits.
Avatar video previews: approve the first frame before rendering
Create an avatar video preview to get first-frame stills, regenerate them if needed, then call generate-video on the preview id to render the final video.
Avatar Face Swap API (Beta): apply an avatar face to a video
Avatar Face Swap 1.0 is a Beta Sume endpoint that applies a ready avatar's face to a short public source video. Required fields, limits, and polling.