Call Sheet · Sound

The best AI models for lip sync

Make a face speak or sing the audio you have. These are Call Sheet's picks for this job, in order, with the reason for each. Call Sheet is a free tool by Melissa Beery that ranks 101 image, video and sound models for a creative job. Its data was last updated on 20 October 2026.

1

Sync lipsync‑2 / sync‑3

Sync Labs

Built only for this. Any language, any footage, priced per second, and sync‑3 handles profiles and hands.

Replaces the mouth in footage you already have to match new audio, in any language.

Cost
Hobbyist US$5 plus US$0.05 per second, watermarked. Creator US$19, no watermark. sync‑3 up to US$0.133 per second
Where
Higgsfield
Rights
No restriction on commercial output found.
Watch out
A static AI face gives static lips, so generate the source already speaking.
How to ask itFront-facing footage already speaking + one clean voice track + model pick (lipsync-2 for most, sync-3 for profiles, close-ups and obstructions)

Face frontal or near frontal, well lit, at least 480p, and large in frame.

One speaker per audio track. Use Segments for a second speaker.

Open Sync lipsync-2 / sync-3 in Call Sheet →
2

Kling Lip Sync

Kuaishou (Kling)

Lip sync on a Kling clip inside the same app, 60 seconds at 1080p through the API.

Adds mouth movement to a Kling clip from an audio file or a typed line.

Cost
Standard US$6.99 promo, 660 credits, 1080p, no watermark
Where
Higgsfield · check in app: OpenArt
Rights
Paid tiers are marked for commercial use.
Watch out
Human faces only, no animals.
How to ask itA Kling clip with a complete human face + uploaded voice or Kling TTS at 0.8x to 2x + (API) face_id and sound_insert_time

The face must be complete and human. Animals are refused.

Keep the clip within the audio length, or expect the audio cropped.

Open Kling Lip Sync in Call Sheet →
3

Higgsfield Lipsync Studio

Higgsfield

Eight engines in one room, on the subscription you already have.

Eight lip sync engines in one room with scene templates.

Cost
Starter about US$9, 120 credits. Plus US$49, 1,000 credits
Where
Higgsfield
Rights
No restriction on commercial output and no separate licence to buy.
Watch out
A carrier, so quality and ceiling change with the engine.
How to ask itSharp front-facing source image or clip + expressive audio generated first + engine pick + scene template (General, Selfie, Podcast, Car Talking)

Source in sharp focus, even light, front‑facing, no heavy makeup or glasses.

Give the source some expression. A flat face animates flat.

Open Higgsfield Lipsync Studio in Call Sheet →
4

Runway Act‑Two

Runway

Act the line yourself on a phone and the character's face follows. A performance, not just a mouth.

Act the line on a phone.

Cost
Standard US$15 (US$12 yearly), 625 credits. 5 credits per second, 3 second minimum
Where
Runway
Rights
Runway claims no ownership of your content.
Watch out
30 seconds, 720p class output, and a real performance recorded per line.
How to ask itDriving performance video (one person, waist up, face visible, no cuts, under 30 seconds) + character image or video + gesture control on for images

One subject, framed no wider than the waist, face visible the whole take.

No cuts in the performance video.

Open Runway Act-Two in Call Sheet →
5

HeyGen Avatar IV & Lipsync

HeyGen

Photo plus script to a 30 minute presenter, with the strictest written consent rule here.

A photo plus a script becomes a presenter with gestures.

Cost
Creator US$29, 600 credits
Where
HeyGen's own site
Rights
You own output on paid plans and commercial use is allowed.
Watch out
Credits burn fast and it is an avatar product first.
How to ask itOne face per photo + script in any of 175 plus languages or an audio file + Speed for a front-facing single speaker, Precision for profiles, hands and groups

Get explicit consent from any real person before building a custom avatar.

Clear audio and a visible face, or accuracy drops.

Open HeyGen Avatar IV & Lipsync in Call Sheet →
6

OmniHuman 1.5 (Dreamina)

ByteDance

The most expressive photo‑to‑performance model, on terms written for private use.

One photo plus a voice becomes a performance that reads the emotion in the audio and moves the whole body.

Cost
Free daily credits. Paid Dreamina Basic exists, price not shown
Where
ByteDance's own site
Rights
Dreamina's terms say the service is for private, non‑commercial use unless additional terms allow it.
Watch out
Private‑use terms and a reported forced watermark on paid output.
How to ask itFront-facing well-lit photo + uploaded audio or a Dreamina voice + line and action description under 240 characters each + Avatar Pro or Turbo

Neutral, front‑facing, evenly lit face. No sharp angles or covered features.

Match the voice's tone and pitch to the face.

Open OmniHuman 1.5 (Dreamina) in Call Sheet →
7

LivePortrait

Kuaishou (open weights)

Free and local. Drives a face from a video you shot, no audio.

Free and local.

Cost
Free, your own GPU
Where
Kuaishou (open weights)'s own site
Rights
MIT code.
Watch out
No audio drive.
How to ask itSource portrait or portrait video + driving video of your own face acting the line (or a saved .pkl motion template) + flags for stitching, eye and lip retargeting

Keep head movement modest. The warp breaks on big turns.

Match framing between source and driver as closely as you can.

Open LivePortrait in Call Sheet →

Side by side

●●● strong · ●●○ middling · ●○○ weak, as rated in Call Sheet
ModelRights clearanceTraining dataVoice consentCost
Sync lipsync‑2 / sync‑3●●○●○○●●○Hobbyist US$5 plus US$0.05 per second, watermarked. Creator US$19, no watermark. sync‑3 up to US$0.133 per second
Kling Lip Sync●●○●○○●○○Standard US$6.99 promo, 660 credits, 1080p, no watermark
Higgsfield Lipsync Studio●●●●○○●●○Starter about US$9, 120 credits. Plus US$49, 1,000 credits
Runway Act‑Two●●●●○○●●○Standard US$15 (US$12 yearly), 625 credits. 5 credits per second, 3 second minimum
HeyGen Avatar IV & Lipsync●●●●○○●●○Creator US$29, 600 credits
OmniHuman 1.5 (Dreamina)●○○●○○●○○Free daily credits. Paid Dreamina Basic exists, price not shown
LivePortrait●●○●○○●○○Free, your own GPU

Describe your own lip sync job in Call Sheet and it ranks every model for it, then writes the prompt.

Open Call Sheet →

More jobs