Skip to main content

sync/lipsync-3/lip-sync

sync.’s lipsync-3 lip-sync endpoint matches an existing face video to a supplied speech recording and returns an MP4. The output follows audio length and billing follows rounded-up source-video seconds.

From $0.162/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 face-video URL; the source must be 1–300 seconds, and its duration rounds up to whole seconds for billing. Trim unused footage before submitting; a source outside the range is rejected before charging. at least 1 characters
1/1
1 / 1 files
Required URL for the replacement speech; WAV and MP3 were used in our tests. The recording sets output length, including trimming or backward extension of picture, without changing the video-based billing quantity. at least 1 characters
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. · LIPSYNC-3

Give an existing face video new dialogue, with the finished MP4 timed to your speech track.

Key numbers

Input-video range
1–300 s
Trim the source to the dialogue you need; billing rounds its duration up to whole seconds.
Required media inputs
2
A face video and a separate speech track determine the lip-sync result.
Measured processing
76/173 s
These approximate times came from two source clips of 5.04 and 5.00 seconds, respectively.
Source rates kept (fps)
24/25
Our 1280×720 and 1358×680 test videos kept their respective frame rates in the returned MP4s.

Before you spend

All modes

Work with footage and voices you have permission to use, and never impersonate a real person. Review the mouth movement and any extension at the end before distributing a re-voiced clip.

Lip sync
  • The source video must run from 1 to 300 seconds. Audio controls the result duration: shorter speech trims the picture, while longer speech extends it by playing frames back from the end.
  • This request takes video_url and audio_url. Built-in text-to-speech, still-image input and the publisher’s sync_mode choices are not exposed here; prepare the speech file before submitting.

What it does

Video plus dialogue

Keep the selected take in your workflow

The source clip supplies the face video and the replacement recording supplies the words. lipsync-3 returns a re-synced MP4, making a corrected presenter line or an authorized translated lesson a concrete input pair rather than a text prompt.

Duration behavior

Plan the ending around the speech

A 6.48-second speech track extended our 5.00-second source to 6.48 seconds by playing picture frames back from the end. Use audio close to the intended shot length when that reversal would distract from the delivery, and review the tail before placing it in an edit.

Media inspection

Retain picture dimensions, check the mix

Both measured clips kept their source resolution and frame rate: 1280×720 at 24 fps and 1358×680 at 25 fps. The output soundtrack is mono AAC, so check your final audio mix separately from picture dimensions.

Publisher positioning

Evaluate difficult facial transitions

sync. says sync-3 uses scene context and handles obstructions automatically in its model documentation. Test a representative head turn or hand crossing in your own footage; our two measured runs establish duration and processing observations, not a scored comparison of those visual situations.

Where it fits

  • Localize a recorded lesson

    Pair lesson.mp4, showing an authorized instructor, with a separately recorded translated lesson.wav. Receive an MP4 whose mouth movements follow that supplied speech; prepare the translation and recording before the lip-sync call.

  • Correct a product announcement

    Submit the original presenter take with a WAV recording of the corrected product name and sentence. The returned video matches the new wording, so you can review the revised line before replacing it in the edit.

  • Prepare regional ad versions

    Reuse a spokesperson clip with separate approved voice-over files for each market. Each submitted video/audio pair produces its own re-synced MP4, and each request’s billing follows the source-video duration.

  • Re-voice an interview excerpt

    Combine an authorized interview excerpt with a replacement MP3 speech track. Inspect the resulting MP4’s final frames when the replacement runs longer: the picture extends backward from the source ending to cover the audio.

Model reference

Sync Lipsync 3 API reference

Sync Lipsync 3 API specifications

Publisher and model
sync. · lipsync-3 (sync-3)
Public API name
sync/lipsync-3/lip-sync
Task
Lip-sync from an existing face video and new speech
Required inputs
video_url and audio_url
Source-video duration
1–300 seconds
Output container
MP4
Picture dimensions and timing
Source resolution and frame rate retained
Output soundtrack
Mono AAC re-encoding
Output duration
Follows audio; trims or extends the source picture
Billing unit
Input-video second, rounded up
Measured processing
About 76 s and 173 s for the two short-clip tests
Unavailable controls
sync_mode, built-in TTS and image input

How to call the Sync Lipsync 3 API

  1. Select and trim the face video

    Choose a take with a readable mouth and measure its duration before upload. Keep the submitted clip within 1–300 seconds and remove footage you do not need to bill.

  2. Finish the replacement speech

    Prepare the spoken line as an audio file; our tests used WAV and MP3. Match its length to the intended edit if you want to avoid trimming or backward extension.

  3. Submit the video and audio URLs

    POST /api/v1/jobs/createTask with model set to sync/lipsync-3/lip-sync and input containing video_url and audio_url. Include your Bearer API key and use the request example below as the JSON body.

  4. Retrieve and inspect the MP4

    Save the returned taskId and query /api/v1/jobs/recordInfo?taskId=YOUR_TASK_ID for completion. Download the finished asset and compare consonants, mouth transitions and the ending with your speech file.

The short version

Start a lipsync-3 edit with a finished speech recording and the exact section of face video you intend to use. The two URL inputs determine the result: video length sets the billable seconds, audio length sets the finished timeline, and a longer recording makes the ending run backward through source frames. Inspect that ending along with the mouth movements and mono AAC soundtrack. Use the measured examples below to plan a trial, compare the same material on lip-sync/v1 when cost matters, and proceed with footage and voices you are authorized to use.

Sync Lipsync 3 API questions