Skip to main content

Sync's Lipsync 2 Pro is the studio-grade, detail-focused tier of Lipsync 2. It reworks recorded mouth movements, retains speaking style according to Sync, and exposes four duration-alignment modes.

From $0.101/s

Workbench

Input

Lip sync
1/1

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

  • 1
1 / 1 files
Required URL for the footage; no default. Choose a clearly visible face, especially for a close-up detail check. Used with every sync_mode; video duration does not directly determine billing, which counts the audio. at least 1 characters
affects price1/1
1 / 1 files
Required MP3 or WAV URL with 1–300 seconds of replacement speech; no default. Applies with every sync_mode. The full uploaded recording supplies the voice and its seconds round up for billing, including when cut_off trims the result. at least 1 characters
Sync Mode
cut_offloopbounceremap
Optional alignment choice: cut_off, loop, bounce, or remap; default cut_off. Used when the media lengths differ. It cuts at the shorter input, repeats video, alternates playback, or retimes video, respectively; audio-second billing is unchanged.
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 PRO · CLOSE-UP DIALOGUE

Rework a recorded line with attention to the small details visible in a close-up.

Key numbers

Accepted audio length
1–300 s
The uploaded recording supplies the voice and the seconds used for billing.
Duration alignment
4 modes
Select cut_off, loop, bounce, or remap; omitting the field selects cut_off.
Replacement recording
MP3, WAV
Supply the new dialogue as an audio file linked through audio_url.
Watchmaker sample height
720p
Our close-up result measured 4.21 seconds at 24 fps with cut_off selected.
Generated-file retention
14 days
Download completed media before the retention window ends and the files are deleted.

Before you spend

All modes
  • Confirm your rights to each face, video, and voice before uploading; every person shown must be an adult. Do not impersonate anyone.
  • Generated files are kept for 14 days and then deleted. Save the finished MP4 during that period.
Lip sync
  • Acceptable audio runs from 1 to 300 seconds in MP3 or WAV format. The supplied video must show a clearly visible face.
  • Supported mode values are cut_off, loop, bounce, and remap. No silence mode, text prompt, or resolution setting is exposed.
  • This tier runs a content filter: Mild inputs processed in our tests; Moderate inputs were refused twice. Refused jobs are not charged.

What it does

OBSERVED CLOSE-UP

Watch the watchmaker deliver a new line

In our tests, a 6.04-second watchmaker shot paired with 4.2 seconds of speech produced a 4.21-second result. Lip detail, teeth, and salt-and-pepper stubble remained visible as his mouth followed the replacement words. The MP4 measured 1280×720 at 24 fps.

PRO TIER

Assess detail where the face fills the frame

Sync says Lipsync 2 Pro emphasizes fine facial detail while retaining the speaker's delivery style without speaker-specific training. A close-up gives an editor a place to inspect that claim in motion. The accompanying cover is an illustration, not a test output.

TIMING AND BILLING

A trimmed result can still bill the full recording

cut_off stops the result at the shorter input, but billing counts the audio you submitted, rounded up. Trim an overlong recording before submission, or use loop, bounce, or remap when the picture needs to span the line. Changing the mode does not change the rate.

Where it fits

  • Revise a watchmaker scene

    Use the supplied close-up as a reference for a short dialogue edit. Inspect the moving mouth, teeth, and stubble while checking that the replacement line reaches its intended ending.

  • Replace an ad read in close-up

    Record revised wording for footage featuring an authorized spokesperson. Pro targets the fine facial detail visible in a tight shot; inspect the delivered edit before using it in the ad.

  • Dub a filmed conversation excerpt

    Prepare the replacement speech recording for the selected shot. Sync says Pro retains the speaking style visible in the source; choose a timing mode that fits the new recording.

  • Fit dialogue to an available take

    Use cut_off for a shorter ending, loop for repeated picture, bounce for alternating playback, or remap to adjust the video timeline. Review any repetition or speed change against the intended scene.

Model reference

Sync Lipsync 2 Pro API reference

Sync Lipsync 2 Pro API specifications

Model publisher
Sync
Model tier
Lipsync 2 Pro; detail-focused, zero-shot lip sync
Public model name
sync/lipsync-2-pro/lip-sync
Required fields
video_url; audio_url
Audio formats
MP3; WAV
Audio range
1–300 seconds
Mode choices
cut_off; loop; bounce; remap
Mode default
cut_off
Billing measure
Uploaded audio seconds, rounded up to whole seconds
Sample output
MP4; 1280×720; 24 fps; 4.21 seconds
Content review observed
Mild processed; Moderate refused; refusals not charged
File retention
14 days, then deletion

How to call the Sync Lipsync 2 Pro API

  1. Choose a detailed speaking shot

    Select footage with a clear face and inspect the intended close-up. Confirm that you can use the footage and the voice recording.

  2. Prepare and measure the audio

    Export the finished line as MP3 or WAV, between 1 and 300 seconds. Remove audio you do not intend to submit, since its full duration is billable.

  3. Set the duration behavior

    Provide video_url and audio_url, then choose a sync_mode or accept cut_off. Compare both input lengths before submitting the asynchronous task.

  4. Check the completed edit

    Retrieve the result through polling or a callback, then inspect speech alignment and close-up detail. Download it within the 14-day retention period.

The short version

Build a Pro trial around a close-up you can inspect and a recording whose timing is already settled. The watchmaker sample offers a concrete reference: a 6.04-second source became a 4.21-second MP4 with visible teeth and stubble after receiving a shorter line. For your own edit, check both facial detail and the final spoken word. Match the mode to the shot, trim unused audio before billing begins, and account for Sync's content review. Save the accepted result within 14 days alongside the inputs you used.

Sync Lipsync 2 Pro API questions