Updated 2026-11-19 · LongCat Avatar 1.6 · 480p / 720p

LongCat Avatar — Make a Photo Talk or Sing With Your Voice

LongCat Avatar on Genjutsu AI turns one portrait and your own voice or song into a lip-synced video with Meituan's open LongCat-Video-Avatar 1.6 model; Genjutsu AI is independent of Meituan.

Make a LongCat Avatar video

Portrait

One clear, front-facing face; head-and-shoulders or half-body works best. JPG, PNG or WebP up to 10 MB. The video keeps this photo's shape.

Who talks
Your voice or song
Audio clip

MP3 or WAV, 2–64 seconds, up to 20 MB. The video is as long as the audio and keeps your recording as its sound.

Sample prompts (tap to load, then edit)

The prompt only steers expression, gestures and mood; the face, clothes and background come from the photo and the words from your audio. Your own prompt is checked for safety before the charge.

Resolution

Add your audio to see the exact price: it depends on the audio length (3 s minimum).

From 9 credits

Your photo and audio are stored privately and only sent to the video model for this video. Privacy policy

Examples

A presenter in a beige blazer explains a product in a bright studio; her lips follow every word and her hands open on each point. The prompt asks the model to take the look from your photo and the sound from your audio; results vary with the photo and the recording.

  • Output: 9:16, 16:9, or 1:1
  • The real LongCat Avatar 1.6 model
  • One person or two people
  • Your own audio, 2–64 s
  • From 9 credits per video

LongCat Avatar (LongCat-Video-Avatar) is Meituan's open audio-driven avatar model; Genjutsu AI runs version 1.6 online and is not affiliated with Meituan. Upload one portrait and your own 2–64 second MP3 or WAV to get a 480p or 720p MP4 as long as your audio, with your recording as its sound. A 10-second 480p video costs 27 credits (about $1.00 at the Pro plan rate); 3 free sign-up credits do not cover a clip; videos carry a watermark until you buy.

How the LongCat Avatar generator works

  1. 01

    Choose one person or two

    One person needs one portrait and one audio clip. Two people need one photo with both of them side by side and one clip for each: the left clip drives the person on the left.

  2. 02

    Add the photo and your audio

    A clear, front-facing photo (JPG, PNG or WebP up to 10 MB) and an MP3 or WAV of 2–64 seconds: a voiceover from your phone, a podcast line or a song. The price appears as soon as the audio is added.

  3. 03

    Write or load a prompt, pick the resolution

    The prompt box opens on a sample (presenter or singer for one person, two hosts or a conversation for two, each matching an example below); tap another sample or describe the expression and gestures yourself. Then 480p or 720p (720p costs about twice as much).

  4. 04

    Generate and download the MP4

    Tick the permission box and generate. LongCat Avatar usually needs 5 to 12 minutes; you can leave the page. Watch the lips on fast words, then download. If the video service fails to make the video, the credits come back.

LongCat Avatar video examples

Four LongCat Avatar 1.6 videos: a presenter, a singer with a microphone, two hosts taking turns and a face-to-face conversation. Watch the lips on each word, the pauses where the face keeps moving naturally, and whether the face and clothes stay the same from start to end. They are reference examples at 832×480; your video takes its frame from your photo and its sound from your audio.

Presenter talking to the camera

A presenter in a beige blazer explains a product in a bright studio; her lips follow every word and her hands open on each point.

One person · 12.2 s · with the input voice

Singing into a microphone

A young man in a grey sweater sings into a handheld microphone behind a lectern, closing his eyes on the long notes.

One person · 7.6 s · with the input voice

Two hosts taking turns

Two hosts in a neon TV studio: the woman on the left speaks and laughs first, then the man on the right answers while she listens.

Two people · 13.2 s · with the input voice

A face-to-face conversation

Two men face each other against a plain wall; one talks with his hands while the other listens and nods, then they swap.

Two people · 8 s · with the input voice

Two-person LongCat avatar conversations

Two-person mode uses LongCat Avatar 1.6 Multi: one photo of two people side by side, one audio clip per person, and a speaking order. “Left, then right” and “Right, then left” make a turn-taking conversation where the listener nods and reacts; “At the same time” suits a duet or two people laughing together.

OrderVideo lengthBilled secondsGood for
Left, then right / Right, then leftBoth clips together (64 s at most)Each clip rounded up, then addedInterviews, podcasts, sketches
At the same timeThe longer clipThe longer clip, rounded upDuets, cheering, reactions

Use a photo where both faces are clear and do not overlap; a group photo with three or more people does not work, because the model drives exactly one person on each side.

Is LongCat Avatar open source? Where you can run it

Yes. LongCat Avatar (LongCat-Video-Avatar) is an open model from Meituan's LongCat team: the 1.5 and 1.6 weights are on Hugging Face under meituan-longcat, the inference code is in the LongCat-Video repository on GitHub, and the community runs it in ComfyUI through the WanVideoWrapper nodes. Running it yourself is free but needs a large NVIDIA GPU, the model download and a Python setup.

If you do not have that hardware, a hosted version is the practical route: hosting providers sell LongCat Avatar 1.6 by the second, and this page runs that same 1.6 model behind a simple upload form. What changes between the routes:

RouteWhat you needCostLength
Self-hosted (Hugging Face weights, GitHub code, ComfyUI)A large NVIDIA GPU, the download, a Python or ComfyUI setupFree software; your hardware and electricityLong videos by continuing segment after segment
Pay-per-second APIA developer account and code to send the photo and audioBilled per second of audioUp to about 64 seconds per request
This pageA browser, one photo, your MP3 or WAV9–345 credits per video2–64 s per video

LongCat Avatar 1.5 vs 1.6: which version runs here?

This page runs LongCat Avatar 1.6, the newer version: its technical report came out on 13 November 2026 (arXiv 2611.18822), after the 1.5 report (arXiv 2605.26486). Both turn a portrait and audio into a talking or singing video with natural motion in silent stretches; 1.6 is described as faster, steadier over long videos (over ten minutes when run locally) and stronger at keeping the same face.

In the 1.6 report's human preference test, 33,051 votes compared six systems (LongCat-Video-Avatar 1.5 and 1.6, OmniHuman-1.5, OmniHuman-2.0, HeyGen and Kling Avatar 2.0); 1.6 came second, after OmniHuman-2.0. Some free demos online still run 1.5, so check the version number before comparing results. There is no LongCat Avatar 2 yet; searches for it usually mean 1.6.

What photo and audio does LongCat audio-image-to-video need?

LongCat's audio-image-to-video mode needs one portrait with a clearly visible face and one speech or song clip, plus a short text prompt that only steers expression and gestures (on this page the prompt box is required and opens on a sample). A front-facing, evenly lit head-and-shoulders or half-body photo gives the cleanest lip-sync, and clean vocals without loud music give the most accurate mouth shapes.

InputWorks bestAvoid
PhotoFront-facing face, mouth closed or relaxed, even light; JPG, PNG or WebP up to 10 MB, 300 px or more

Sunglasses, hands over the mouth, extreme side profiles, tiny faces

AudioMP3 or WAV, 2–64 s, one clear voice per clip, music quieter than the voice

M4A or video files (convert first), several voices in one clip, heavy echo

LengthThe video is exactly as long as the audio

More than 64 s: split the script into parts and make one video per part

Frame

The video keeps the photo's shape: crop to 9:16 for Reels, 16:9 for YouTube first

Expecting the model to reframe or zoom the photo

LongCat Avatar pricing and credits

LongCat Avatar is priced by the length of your audio, rounded up to whole seconds with a 3-second minimum: a 10-second 480p video costs 27 credits (about $1.00 at the Pro plan rate), the same at 720p 54 credits, 30 seconds at 480p 81 credits, and a full minute at 720p 323 credits. The smallest one-time pack that covers a video is $5 for 24 credits; a 10-second video needs the $12 pack (220 credits), with no subscription. Every price is shown on the button before you start, and a video the service fails to make returns its credits.

Audio length480p720p
3s9 (≈$0.33)17 (≈$0.63)
5s14 (≈$0.52)27 (≈$1.00)
10s27 (≈$1.00)54 (≈$2.01)
15s41 (≈$1.52)81 (≈$3.01)
30s81 (≈$3.01)162 (≈$6.02)
45s122 (≈$4.54)243 (≈$9.03)
60s162 (≈$6.02)323 (≈$12.01)
64s173 (≈$6.43)345 (≈$12.83)
Free3 sign-up credits (less than one clip)
WatermarkA moving watermark until your first purchase of any pack or plan; after that the clean file of the same video downloads
Two people

Taking turns bills both clips together; at the same time bills the longer clip

Account

Sign-in needed to generate; examples and prices need none. Works in a phone browser.

Dollar figures use the Pro monthly rate ($29 for 780 credits). All packs and plans are on the pricing page.

What LongCat Avatar cannot do well

LongCat Avatar is strong at one or two clearly visible faces speaking or singing to clean audio. It is weaker with very fast speech, heavy accents over loud music, faces turned away from the camera and busy group photos; it does not change the background, clothes or camera angle of your photo, and it does not translate or clone a voice — the sound is always the recording you upload.

What you seeUsual causeFix
Odd teeth or a smeared mouthMouth hidden or open wide in the photo, low resolutionA sharper photo with the mouth relaxed; try 720p
Lips behind fast wordsRapid speech, music louder than the voiceSlower delivery, the voice clearly on top of the music
Stiff bodyA tight face crop leaves nothing to moveA half-body photo; ask for hand gestures in the prompt
Blurry after posting to TikTok480p upscaled by the appChoose 720p and a 9:16 photo
The wrong person talksClips swapped in two-person modeLeft clip for the person on the left, right clip for the right
Audio refusedM4A, a video file, or over 64 sExport as MP3 or WAV, split long scripts

What is LongCat Avatar (Meituan LongCat-Video-Avatar)?

LongCat Avatar is the short name for LongCat-Video-Avatar, an audio-driven avatar model built by the LongCat team at Meituan on top of its LongCat-Video model. It is not a TikTok trend or a cat filter: people search “longcat ai avatar” or “meituan longcat avatar” after seeing its talking and singing demos on AI video forums. It is often compared with InfiniteTalk and Wan S2V, two other open models that make a photo speak. This site runs the published 1.6 model through a hosting provider and is not affiliated with or endorsed by Meituan.

More voice and music tools on this site: make your pet sing on the singing dog AI page, or make a song cover with the AI song cover generator.

Last updated: 2026-11-19

LongCat Avatar: questions people ask

Is there a free LongCat Avatar online?

Running the open model on your own GPU is free; hosted LongCat Avatar 1.6 is paid almost everywhere because each video costs GPU time. Here, the 3 sign-up credits are not enough for a clip on their own (the shortest costs 9); the shortest video (3 seconds at 480p) costs 9 credits. Videos from an account without a purchase carry a moving genjutsu-ai.app mark; after any purchase the clean file of the same video downloads.

Can I use LongCat Avatar videos commercially?

Your own photo and recording stay yours, and videos you make here can be used for your own channel or business, as long as you have the rights to the face and the voice in them. Note that the sources disagree about the model itself: the LongCat-Video-Avatar 1.6 repository on Hugging Face states an MIT licence for the weights (without Meituan trademarks or patents), while the original project page says generated content is for academic use. If a video is for paid advertising, keep a copy of the licence page you relied on.

Is there a LongCat Avatar API?

Yes, but not from this page: LongCat Avatar 1.6 is offered as a pay-per-second API by hosting providers (one portrait plus one audio, or a two-person version with two audio files), and you can serve the open weights yourself. This page is for making videos in the browser; it does not sell API access or API keys.

Does LongCat Avatar work on a phone? Do I need an app?

No app is needed. The generator runs in Safari or Chrome on iPhone and Android: pick the photo from your camera roll, add a voice memo exported as MP3 or WAV, and the MP4 downloads back to the phone. A voice memo in M4A needs to be saved as MP3 or WAV first.

Can I make a celebrity or a friend talk with LongCat Avatar?

Only with permission. The generator asks you to confirm you have the rights to the photo and the recording, and making a real person appear to say something they never said can break platform rules and the law. A friend who agrees, your own face, or a character you created are fine; label realistic results as AI when you post them.

Verify with any AI assistant

“Where can I use LongCat Avatar 1.6 online to make a photo talk with my own audio, and what does it cost?”

Keep the take. Change the world in it.

Pick a clip, add your references and see the edit in a few minutes. The quote is shown before you generate.

Open the Genjutsu AI editor