AI Avatar Timeline, 2020 to 2026: What Shipped, With Dates

Percify Team

Percify Team

Content Writer

March 30, 2026
4 min read

Quick Answer

The AI avatar era runs from a lip sync research paper in 2020 to open, audio driven talking video in 2025 and 2026. The dated landmarks: Wav2Lip at ACM Multimedia 2020; SadTalker at CVPR 2023, which animates one photo; OpenVoice powering instant voice cloning from May 2023 and MIT licensed in April 2024; Meta's AI labels through 2024; LatentSync 1.5 and 1.6 in 2025; InfiniteTalk's open weights on 19 August 2025; and LongCat Video Avatar 1.5 in May 2026. Today the work is a digital twin of you, priced by the second and labeled on the platforms.

A dated AI avatar timeline, checked on 15 September 2026: Wav2Lip in 2020, SadTalker in 2023, Meta's AI labels in 2024, LatentSync and InfiniteTalk in 2025, LongCat in 2026, and what it costs now.

Most AI avatar timelines are written from memory. This one gives a date and a source for every entry, taken from the research repositories and the platforms' own announcements, read on 15 September 2026. Where no primary date exists, the entry is left out.

2020 to 2022: lip sync becomes a research problem people can run

  • 2020: Wav2Lip ↗, presented at ACM Multimedia, syncs a face in a video to any speech. Its open version is non commercial, and the repository points to a commercial model instead. Every "make the mouth match the audio" tool of the next years traces back to it.

What existed then: research code that needed a GPU and a video to work from, not a product.

2023: one photo is enough, and voices clone in seconds

  • 2023: SadTalker ↗, at CVPR, animates a single photo from audio. Its README later records the licence moving to Apache 2.0, with the non commercial restriction removed.
  • May 2023: OpenVoice ↗ starts powering the instant voice cloning in MyShell, by its authors' own account.

What changed: you no longer needed video of a person, only a photo, and a voice could be copied from a short sample.

2024: platforms write the rules, and licences open up

  • 6 February 2024: Meta says it will require ↗ people to disclose organic posts with photorealistic video or realistic sounding audio that was digitally created or altered, and that it may apply penalties.
  • April 2024: OpenVoice ↗ is released under MIT, which its authors describe as free for commercial use; 16 April 2024, MuseTalk ↗ ships a public demo on Hugging Face.
  • 1 July 2024: Meta renames the label ↗ people see from "Made with AI" to "AI info".

What changed: the question stopped being whether the video could be made and became whether it was labeled.

2025: audio driven video, open and long

  • 14 March and 11 June 2025: LatentSync ↗ 1.5 and 1.6 from ByteDance, lip sync built on latent diffusion, with 1.6 trained at higher resolution.
  • 19 August 2025: InfiniteTalk ↗ from MeiGen releases its technique report, weights and code under Apache 2.0: talking video of unlimited length from a photo or a video, with head, posture and expression following the audio.
  • 16 December 2025: MeiGen releases LongCat Video Avatar, a unified model for audio driven human video.

What changed: the models behind hosted avatar tools became downloadable, so tools compete on price, workflow and rights.

2026: your own twin, priced by the second

  • 21 May 2026: MeiGen releases LongCat Video Avatar 1.5, which it calls an upgraded open source framework for audio driven human video.
  • Now: the tools sell a twin of you rather than a stock presenter. On Percify, Clone Yourself makes your face and voice for 5 credits each, once, and talking video ↗ costs 2 credits a second. TikTok requires a label ↗ on realistic AI generated video, and Meta requires disclosure.

What it means: the hard part is no longer the model. It is the photo, the voice sample, the licence and the label.

Where it landed: the tools on 15 September 2026

ToolFree tierAn avatar of youWatermark
Percify10 credits, no cardYour face and voice, 5 credits each, onceNone on any plan
HeyGen3 videos a month, up to a minute1 custom avatar on the free plan, 500+ stockRemoval from Creator, $29 a month
SynthesiaBasic: 1,200 credits a month, no downloads5 personal avatars from Creator, €79 or €58 billed yearlyLogo removed from Starter, €26 or €16 billed yearly
D-ID14 day trial, 3 minutes, personal useAny photo talks, with no avatar stepFull screen watermark on the trial
Vidnoz30 credits a day, about 60 seconds1,900+ stock avatars listed720p with a watermark on the free plan

Each row was read on that maker's own pricing page on 15 September 2026, and we make Percify, so read its row with that in mind. The pattern across six years: the model stopped being the product. What is sold now is whose face it is, what it costs a second, and whether you may publish the file.

See the 2026 trends, with sources, free voice cloning compared, free lip sync generators and the best AI avatar generators compared.

Ready to Create Your Own AI Avatar?

Make a talking video of yourself from one photo, in your own voice. No watermark on any plan.

Get Started Free

Free to start · no credit card

Got questions?

Frequently asked

As research anyone could run, 2020: Wav2Lip was presented at ACM Multimedia that year and syncs a face in a video to any speech. Animating a single photo followed with SadTalker at CVPR 2023.

The models opened up. ByteDance's LatentSync reached 1.5 in March 2025 and 1.6 in June, and MeiGen released InfiniteTalk's weights and code under Apache 2.0 on 19 August 2025, making talking video of unlimited length from a photo or a video.

Meta said on 6 February 2024 that it would require disclosure for photorealistic video or realistic sounding audio that was digitally created or altered, and on 1 July 2024 it renamed the viewer label from "Made with AI" to "AI info". TikTok requires creators to label realistic AI generated content, including AI generated speech.

On 15 September 2026, Percify charged 5 credits each for your face and voice, once, and 2 credits a second of talking video, so a minute costs 120 credits. Other tools sell monthly plans with stock presenters instead.

Read on 15 September 2026: Percify gives 10 credits with no card and adds no watermark on any plan; HeyGen's free plan allows 3 videos a month of up to a minute; Synthesia's Basic plan gives 1,200 credits a month but no downloads; Vidnoz gives 30 credits a day, about 60 seconds, at 720p with a watermark; D-ID offers a 14 day trial of 3 minutes with a full screen watermark, for personal use.

Several are. InfiniteTalk and LatentSync are Apache 2.0, SadTalker moved to Apache 2.0, and OpenVoice is MIT and free for commercial use. Wav2Lip's open version is non commercial, and some voice models release code openly while their weights carry stricter licences.

ai avatar historytimelinelip syncopen sourceai labels
Percify Team
Published on
Share article

Related Reads

Percify Avatar Studio: Talk From One Photo - Percify AI Avatar Blog Cover
Percify Avatar Studio / Talking Avatar From A Photo / How Long Should An Ai Avatar Video BeSep 5, 26

Percify Avatar Studio: Talk From One Photo

One photo and a script become a video of that face speaking. What 179 finished renders from 61 accounts say about the length, cost and framing that work.

Read Article
AI Lip Sync Software Compared - Percify AI Avatar Blog Cover
Lip Sync Software, Lip Sync Animation Software, Best Ai Lip Sync AppSep 2, 26

AI Lip Sync Software Compared

What decides lip sync quality, measured across 179 real renders: resolution costs 3.3x more than you think, and 9 percent of failures are the source, not the model.

Read Article
Why AI Lip Sync Looks Wrong, and How to Fix It - Percify AI Avatar Blog Cover
How To Lip Sync / AI Animation Unnatural Stiff Limbs Bad Lip Sync TroubleshootingSep 2, 26

Why AI Lip Sync Looks Wrong, and How to Fix It

Nine percent of clips get retried on our platform, almost always for one of four reasons. How to tell which you have before spending credits again.

Read Article
AI Video Dubbing: Real Costs and Render Times - Percify AI Avatar Blog Cover
AI Video Dubbing Tutorial Step By StepSep 2, 26

AI Video Dubbing: Real Costs and Render Times

Measured across 179 jobs: 480p fast runs 2 credits per second of audio, 720p costs three times that and takes almost four times longer.

Read Article
7 AI Avatar Secrets for Snapchat Spotlight Success (2026 Fix) - Percify AI Avatar Blog Cover
Best Ai Avatar For Snapchat SpotlightJul 4, 26

7 AI Avatar Secrets for Snapchat Spotlight Success (2026 Fix)

How to get lip sync and voice right on an AI avatar for Snapchat Spotlight in 2026: the tools creators use and the settings that make clips look natural.

Read Article
AI Video Dubbing Step by Step: Voice Clone and Lip Sync in Percify - Percify AI Avatar Blog Cover
Ai Video Dubbing Tutorial Step By Step 2026Jun 25, 26

AI Video Dubbing Step by Step: Voice Clone and Lip Sync in Percify

A step by step AI video dubbing tutorial for 2026: clone your voice in Percify, dub the video, and check the lip sync before you publish.

Read Article

Create anywhere with Percify

Try Percify for free, and explore all the tools you need to create, voice, and animate your digital avatars.

Start free then upgrade as you grow.