Skip to main content

Sync's Lipsync 2 is its standard-tier, zero-shot lip-sync model. Sync says it retains the speaker's delivery style; this endpoint pairs 1–120 seconds of video with replacement audio and five timing modes.

From $0.06/s

Workbench

Input

Lip sync
affects price1/1

Drop a video here, or browse · 1 file · Max 90 MB · MP4 · WEBM

  • 1
1 / 1 files
Required URL for the existing video; keep the face clearly visible and duration within 1–120 seconds. No default applies. Its seconds round upward for billing in every sync mode, including when the result is shorter. at least 1 characters
1/1
1 / 1 files
Required MP3 or WAV URL containing the replacement words and voice, with no default. The recording does not change the video-based charge in any mode; output timing depends on its length and sync_mode. at least 1 characters
Sync Mode
cut_offloopbouncesilenceremap
Optional in every request; default cut_off. Values: cut_off (shorter input), loop (repeat video), bounce (forward/reverse), silence (pad shorter audio), remap (retime video to audio). All five use the same video-based charge.
Safety checkerOff

SpicyAPI does not run a safety checker on this model. Your prompt and media go to the model as written, and the model itself decides what comes back.

Checking your account before enabling submission and pricing.

Output

Ready for a new run
Example result

Related models and next tasks

Missing the model you need?

SYNC · STANDARD TIER

Replace the spoken line and choose how the video fits its timing.

Key numbers

Source-video window
1–120 s
The submitted clip must fit this range; video over 120 seconds is rejected at acceptance.
Duration modes
5
Choose trimming, looping, forward/reverse playback, silence padding, or retiming through sync_mode.
Default timing rule
cut_off
Without a mode selection, the result stops at the shorter input's ending.
New dialogue formats
MP3, WAV
Supply a finished recording; its duration does not alter the video-based bill.
Download window
14 days
Save completed MP4 files before their retention period ends and they are deleted.

Before you spend

All modes
  • Secure permission for the faces, footage, and voices in your request. Every person shown must be an adult. Impersonation is prohibited.
  • Each finished Lipsync 2 clip can be downloaded for 14 days before the platform removes it. Keep a downloaded copy of any result you intend to retain.
Lip sync
  • Submit video between 1 and 120 seconds. Longer clips are rejected during request validation.
  • Public inputs are video_url, audio_url, and sync_mode. There is no text-prompt field; finish the MP3 or WAV recording before creating the task.
  • Billing measures the input video even if a duration mode returns a shorter MP4. Trim unused footage before upload to reduce the submitted duration.

What it does

LOOP TRIAL

The tailor finishes a longer invitation

Our atelier example began with 5.04 seconds of footage and a 6.5-second line. With loop selected, the returned video lasted 6.5 seconds: the source repeated while the mouth delivered the full recording. Its picture measured 864×496 at 24 fps.

SPEAKING STYLE

A smile and eyebrow lift carry through

The tailor's small smile and raised eyebrow remained in our result after his dialogue changed. Sync says Lipsync 2 learns speaking style from the source without training on that person. Treat this clip as a concrete observation of that behavior, then inspect your own speaker's delivery.

TIMELINE CHOICES

Fit the ending to the edit you need

Use cut_off to stop at the shorter input, silence to pad a shorter recording, or remap to change video timing to fit the audio. Loop and bounce extend short footage by repeating it or alternating playback direction. Each choice uses the same input-video billing rule.

Where it fits

  • An after-hours shop invitation

    Follow the tailor example with an authorized shop clip and a longer recorded invitation. The loop mode can repeat the visual take until the audio ends; check the restart before sharing the result.

  • A translated presenter segment

    Prepare a translated MP3 or WAV for an existing presenter clip. Sync says speaking style can carry across languages; the endpoint matches the supplied recording rather than writing or translating the line.

  • Dialogue for a generated character

    Sync says Lipsync 2 works with animated and AI-generated people as well as live footage. Bring an existing character video and replacement speech, then choose a duration mode for that pair.

  • A corrected tutorial sentence

    Trim the instructor's take to the sentence being changed and record its replacement. Video seconds determine billing, so preparing that short source matters even when cut_off makes the result shorter.

Model reference

Sync Lipsync 2 API reference

Sync Lipsync 2 API specifications

Model and tier
Sync Lipsync 2; Sync's standard tier
Callable model name
sync/lipsync-2/lip-sync
Video duration accepted
1–120 seconds
Dialogue formats
MP3 and WAV
Optional timing field
sync_mode; default cut_off
Available timing values
cut_off, loop, bounce, silence, remap
Billable duration
Input-video seconds, rounded upward to whole seconds
Delivery
Asynchronous task; MP4 result
Measured loop result
6.5 s; 864×496; 24 fps
Generated-file retention
14 days before deletion

How to call the Sync Lipsync 2 API

  1. Measure the source passage

    Choose footage where the face is clear and trim it to the intended passage. Confirm that the video runs 1–120 seconds before uploading it.

  2. Finish the dialogue file

    Record the replacement words or prepare them separately as speech, then supply an MP3 or WAV URL. Compare its duration with the video to plan the ending.

  3. Choose the duration rule

    Create a sync/lipsync-2/lip-sync job using the source and dialogue URLs plus your chosen sync_mode. Omit the mode for cut_off, or choose loop, bounce, silence, or remap for a different timing treatment.

  4. Follow the task to completion

    Keep the asynchronous task ID and poll or use a completion callback to retrieve the MP4. Inspect the new dialogue and any timeline changes, then save the file within 14 days.

The short version

Measure the video before choosing how to fit the dialogue. A loop can let a short take cover a longer recording, while cut_off can end an edit early; both still bill the submitted video's rounded-up seconds. Our tailor sample shows a full 6.5-second invitation with the original smile and eyebrow lift, and the separate cut_off trial shows why the finished length can be shorter than the billed duration. Bring footage and audio you have permission to use, compare the ending with your intended edit, and download the MP4 during its 14-day availability window.

Sync Lipsync 2 API questions