Providers and ModelsPixVerse

Pixverse Lip Sync

Pixverse Lip Sync
PixVerse · Video Generation
POST /v1/videos/generations

Aligns mouth movement in an existing video to an uploaded audio track or to text spoken by one of fourteen built-in voices.

At a glance

FieldValue
Model idpixverse-lipsync
Model release date2025-07-14
Input modalitiesText, Video, Audio
Output modalitiesVideo
Context window-
Weight precision-
Featureslipsync, audio_in, video_editing
Native inferenceNo
NewNo
Supported endpointsPOST /v1/videos/generations
Alternate model idspixverse/lipsync

Pricing

ChargeSpecRate
Speechper second$0.08

Example request

$curl https://api.empiriolabs.ai/v1/videos/generations \
>  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
>  -H 'Content-Type: application/json' \
>  -d '{"model": "pixverse-lipsync", "prompt": "sunrise over the ocean", "duration": 6}'

Parameters

ParameterTypeRequiredDefaultDescription
lip_sync_tts_contentstringno-The line to speak. Used when no audio file is attached. Billed in 15-character blocks.
lip_sync_tts_speaker_idenumno"Auto"Voice used for the spoken line. Auto picks one to suit the clip. Ignored when an audio file is attached. · Allowed: Auto, Emily, James, Isabella, Liam, Chloe, Adrian, Harper, Ava, Sophia, Julia, Mason, Jack, Oliver, Ethan
videostringno-Source video URL. Required.
audiostringno-Audio URL to lip sync to. Takes precedence over the spoken text.

Notes

Aligns mouth movement in an existing video to speech, either from an audio file you supply or from text spoken by a built-in voice.

Inputs

  • video: the source clip, up to 300 seconds and 250MB.
  • audio: the speech to match, up to 300 seconds and 250MB.
  • Or lip_sync_tts_content with lip_sync_tts_speaker_id to have the model speak your text. Fourteen named voices are available plus Auto, which picks one to suit the clip.

Billing

  • Billed per second of speech. Text-to-speech input is metered in 15-character blocks at the same rate, so the charge tracks the length of the script rather than the length of the source video.

Input limits

  • Video: MP4, MOV or WebM, up to 1920px on the long edge.
  • Audio: MP3, WAV, M4A or AAC.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/pixverse-lipsync.