lipsync-2 and lipsync-2-pro
lipsync-2 is Sync's general-purpose lipsync model, preserving each speaker's individual speaking style at 512x512 resolution. lipsync-2-pro adds diffusion-based super resolution for better detail around beards, teeth and facial features at the same base resolution, running 1.5-2x slower.
- Up to
- 1800 seconds
- Resolution
- 512x512
- Weights
- Not released
- API
- Yes
- Commercial use
- Not established
Both require natural speaking motion in the input video and cannot work from still frames; both support active speaker detection for multi-person footage and are available in Studio and via API. A legacy lipsync-1.9.0-beta remains available as the cheapest and fastest option.
The research notes for this model record other terms but do not state a commercial-use position, and no licence page was retrieved, so it is not established here. Check the vendor's own terms.
- Depends on your plan tier. Paid plans remove watermarks
- Output is watermarked. Paid plans remove watermarks
- Requires consent from the person depicted. Consent requirements for syncing a real person's likeness not stated on the pages fetched
Specification
- What it takes in
- video, audio, text
- What it makes
- video
- Maximum duration
- 1800 seconds
- Maximum resolution
- 512x512
- Aspect ratios
- not established
- Controls
- lipsync, voice-clone, translation
- Weights
- Not released
- API
- Yes
- Pricing
- Usage on top of a subscription: lipsync-2 at $0.04-$0.05/sec at 25fps, lipsync-2-pro at $0.067-$0.083/sec, lipsync-1.9.0-beta at $0.02-$0.025/sec. Subscription tiers Hobbyist $5/mo, Creator $19/mo, Growth $49/mo (5% usage discount), Scale $249/mo (20% usage discount), Enterprise custom.
- Released or updated
- not established
Supported aspect ratios is not established here. That means no page we could retrieve stated it, not that the model lacks one.
Strengths
- Preserves the original speaker's speaking style rather than imposing a generic mouth
- Roughly a third to half the cost of sync-3
- Active speaker detection on multi-person footage
- Explicit published per-second pricing per model
Weaknesses
- 512x512 base resolution, so close-ups will be soft without the pro super-resolution pass
- Fails on still or near-still input; requires natural speaking motion
- lipsync-2-pro is 1.5-2x slower than lipsync-2
- Clip length ceiling depends on subscription tier
Best for
- Bulk dubbing and localisation where cost matters
- Mid-shot and wider dialogue
- Multi-speaker interview footage
Where the sources disagree
Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.
- 512x512 is documented as the working resolution for both lipsync-2 and lipsync-2-pro; lipsync-2-pro applies diffusion super resolution on top, but its final output resolution is not published. maxDurationSeconds of 1800 is the Scale-plan ceiling, not a model limit. Sync's dubbing story relies on external TTS such as ElevenLabs rather than a native dubbing endpoint, though the pricing page separately advertises dubbing into 29 languages.
What to understand before using it
Explainers naming the mechanisms this model's own documentation mentions.
See it from the vendor
Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.
Nearby in the directory
sync-3
Sync's flagship lipsync model and the current default for all users. Processes an entire shot holistically rather than in snippets, which lets it hand
Lip sync and avatars
Flawless DeepEditor and TrueSync
Neural performance editing tools for film and episodic post. DeepEditor applies new dialogue to existing shots and refines performances, covering in-v
Lip sync and avatars
Hedra character / avatar platform
Character and avatar video platform that has grown into a unified inference API putting multiple leading image, video and audio models behind one API
Lip sync and avatars