Quick Answer
The best free lip sync animation software is Rhubarb Lip Sync, which reads a recording and times the mouth shapes for you, with Papagayo-NG for timing by hand; Adobe Character Animator’s Starter mode is also free and syncs from your microphone. To make a still character image talk without a rig, AI tools such as Percify and Hedra render the finished video.
Prices and features read from each maker’s own page on 15 September 2026.
Lip sync animation software compared on 15 September 2026: free tools like Rhubarb Lip Sync, Papagayo-NG and Character Animator, paid suites like Moho and Cartoon Animator, and AI that makes a still character talk.
Related next steps
Lip sync animation software comes in two kinds. Timing tools listen to your dialogue and tell your rig which mouth shape to show when: Rhubarb Lip Sync and Papagayo-NG are free, and suites such as Moho and Cartoon Animator build animation around them. AI tools skip the rig: you give them one image of a character and an audio file, and they render the talking video. Which you want depends on whether you are animating a character or need a finished clip.
Every price below was read on the maker's own page on 15 September 2026.
Lip sync animation software at a glance
| Tool | Price (15 Sep 2026) | What it does | What you get | Best for |
|---|---|---|---|---|
| Rhubarb Lip Sync ↗ | Free, open source | Reads a recording and picks a mouth shape for each moment | Timing files (TSV, XML, JSON) and plugins | Automatic timing for a 2D rig |
| Papagayo-NG ↗ | Free, GPL licence | Breaks your dialogue into phonemes to line up against the audio | Mouth timing to use in your animation program | Timing by hand, phoneme by phoneme |
| Adobe Character Animator ↗ | Starter mode free; more with Creative Cloud | Automatic lip sync and face tracking from your microphone and webcam | An animated character | Performing a character live |
| Blender ↗ | Free, open source | A full 3D suite; you animate the mouth yourself, for example with shape keys | Rendered animation | 3D characters, by hand |
| Moho ↗ | Debut $59.99, Pro $399.99 | 2D rigging and animation; Rhubarb Lip Sync plugs into it | Rendered animation | 2D character rigs |
| Cartoon Animator 5 ↗ | $69 a year (Pro annual plan), 30 day trial | Turns images into animated characters, with face tracking and voice sync | Rendered animation | Quick 2D characters from images |
| Hedra ↗ | Free to start; $15 a month for 1,500 credits | AI avatar models, its own | A finished video | Talking avatars without a rig |
| Percify | Free plan; Starter $6.99 a month, Creator $26 | AI lip syncs a portrait image to any audio (InfiniteTalk) | A finished video | Talking portraits and characters with a face, no rig |
Free lip sync animation software
Rhubarb Lip Sync ↗ is the closest thing to automatic lip sync for a 2D rig, and it is free and open source. Give it a recording and it chooses a mouth shape for each moment, using the classic set from closed lips for P, B and M to a wide open mouth for AA. It recognizes English speech directly and other languages by sound alone. It plugs into Adobe After Effects, Moho, OpenToonz, Spine and Vegas Pro, and its command line writes TSV, XML or JSON for anything else.
Papagayo-NG ↗, free under the GPL, is the hands on option: you type the dialogue, it breaks it into phonemes, and you line them up against the waveform while a preview mouth shows each shape. Slower than Rhubarb, but you decide every beat.
Adobe Character Animator ↗ works differently: you perform, and it animates. Its page describes automatic lip sync plus face and body tracking from your microphone and webcam, and its Starter mode is free.
Blender ↗ is free and open source, forever by its own licence, and it will render any character you can build. It does not time the mouth for you; animators key the mouth shapes against the audio, for example with shape keys.
Paid animation suites
Moho ↗ sells Moho Debut at $59.99 and Moho Pro at $399.99, with a free trial. Rhubarb Lip Sync lists Moho among the programs it plugs into, so the timing it writes drives a Moho rig directly.
Cartoon Animator 5 ↗ from Reallusion turns still images into animated characters and drives faces with your own expressions through a webcam, with voice sync for dialogue. Its Pro annual plan was $69 a year per licence (down from $99), with a 30 day free trial.
AI lip sync: make a still character talk
If you do not have a rig and do not want one, an AI model can take a single image and an audio file and render the whole talking clip.
- Percify runs InfiniteTalk, a model built to "lip sync any portrait to any audio". InfiniteTalk Fast ↗ costs 2 credits a second of audio; InfiniteTalk ↗ costs 4 at 480p and 6 at 720p. On the Creator plan ($26 for 1,233 credits) that is about $2.53 a minute on Fast. There is a free plan, no plan adds a watermark, and every plan carries commercial rights.
- Hedra ↗ builds its own AI avatar models. It is free to start, then $15 a month for 1,500 credits, with commercial use on its paid plans.
Where AI stops. You get a video, not mouth timing for a rig, so you cannot keep editing the animation frame by frame. InfiniteTalk is built for portraits, so characters with a readable face work best; for a character whose mouth is a single line or an animal snout, a timing tool and a rig give you more control.
How to choose
- You have a 2D rig and want automatic timing: Rhubarb Lip Sync, free, into After Effects, Moho, OpenToonz or Spine.
- You want to set every mouth shape yourself: Papagayo-NG.
- You would rather perform the character than key it: Adobe Character Animator, free in Starter mode.
- You animate in 3D: Blender, with the mouth keyed by hand.
- You have one image and a voice line and need the clip today: an AI tool such as Percify or Hedra.
Check the sync before you export
Whatever the tool, the same four things give a lip sync away:
- Closed lips on P, B and M. If the mouth stays open on those sounds, viewers notice first.
- Held vowels. A long vowel needs the mouth to hold its shape, not flutter.
- Clean audio. Background music and noise confuse both timing tools and AI models; sync against a clean voice track and add the music after.
- Pace. Very fast speech gives the mouth no time to form shapes; slow the read slightly rather than fixing it frame by frame.
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 FreeFree to start · no credit card
Got questions?
Frequently asked
For automatic timing, Rhubarb Lip Sync: it is free and open source, reads a recording and picks the mouth shapes, and plugs into After Effects, Moho, OpenToonz and Spine. For timing by hand, Papagayo-NG, free under the GPL. Adobe Character Animator's Starter mode is also free and syncs from your microphone (their own pages, 15 September 2026).
Yes. Rhubarb Lip Sync times the mouth shapes from a recording by itself and exports them for a 2D rig, and Adobe Character Animator lip syncs automatically while you perform through your microphone and webcam.
It can make a still character image talk: Percify's InfiniteTalk takes an image and an audio file and renders the video. InfiniteTalk is built for portraits, so characters with a readable face work best, and the result is a finished video rather than timing you can keep editing in a rig.
Many options are free: Rhubarb Lip Sync, Papagayo-NG, Blender, and Character Animator's Starter mode. On their pages on 15 September 2026, Moho Debut was $59.99 and Moho Pro $399.99, Cartoon Animator 5's Pro annual plan $69 a year, and Hedra $15 a month; Percify has a free plan, then Starter at $6.99 a month.
Blender is free and can render any character, but it does not time the mouth to audio by itself. Animators key the mouth shapes against the soundtrack, for example with shape keys.
