HeyGen Lip Sync (Precision)

Available

HeyGen · heygen/lipsync-precision

Open in workspace

Tasks using this model

Video Lip Sync

Input contract

Required inputs: audio, video
Optional inputs: disable_music_track, enable_dynamic_duration, enable_speech_enhancement
Output: video (uri)
Submission: Official Replicate model endpoint (always current version)

Provider billing

$0.0667 per output second

Provider-side unit, for reference only. This site charges a fixed credit tier per execution — the price shown at quoting time is the price paid.

Contract notes

Re-locked 2026-10-06 (batch E): latest version 03d0f07dd626 carries a field-identical schema vs the A0 snapshot; schemaVersion updated in lockstep. Same dynamic-duration pin, billing basis and measured OFF behavior as lipsync-speed (3 s video + 3 s speech → 3.000 s output, 2026-10-06). Same input contract as lipsync-speed but a separate model and rate; presented as the "precise" mode of one lip-sync task — not an automatic retry of the speed model. Enabled 2026-10-06: batch E deployed-app E2E green (batch-e-e2e report).

Status

This model is catalogued and its contract is locked, but real executions have not passed acceptance yet. Nothing on this page should be read as a claim that it is usable today.

License: Official model; commercial terms not yet reviewed.
Last verified: 2026-10-05

Sources

All models