LTX-2.3 Lipsync
Model Information
Display Name: LTX-2.3 Lipsync
API Model ID: lightricks/ltx-23-lipsync
Category: Audio To Video
Description: LTX-2.3 Lipsync is Lightricks' latest lip-synchronization model, built on the LTX-2.3 architecture. It generates realistic talking-head videos from a portrait image and an audio clip (5–20 seconds), automatically synchronizing lip movements to the speech. ## Key Features - **Audio-driven generation** — the audio clip controls both the video duration and lip movements, producing natural speech synchronization - **Optional portrait reference** — provide a face image for character consistency, or let the model generate one - **Prompt guidance** — use text prompts to influence facial expressions, lighting, and style - **Multi-resolution output** — choose between 480p, 720p, or 1080p depending on quality and budget needs - **Reproducible results** — seed parameter for deterministic generation ## Best Use Cases - AI avatars and virtual presenters for marketing and training videos - Dubbing and localization — reanimate a speaker with translated audio - Social media content creation with talking characters - Podcast and audiobook visualization - Accessibility — adding visual speech to audio-only content ## Parameters | Parameter | Type | Required | Default | Description | |-----------|------|----------|---------|-------------| | audio | URL | Yes | — | Audio file URL (5–20 seconds) | | image | URL | No | — | Portrait reference image | | prompt | string | No | — | Style and expression guidance | | resolution | string | No | 720p | Output quality: 480p, 720p, 1080p | | seed | integer | No | random | Seed for reproducibility | ## Pricing Cost is calculated per second of audio duration, varying by output resolution. A 10-second clip at 720p costs approximately /bin/bash.42.
How to Use This Model
To use LTX-2.3 Lipsync via the HInow.ai API, use the model ID: lightricks/ltx-23-lipsync
API Request Example
POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
{
"model": "lightricks/ltx-23-lipsync",
"messages": [
{"role": "user", "content": "Your input here"}
]
}
Pricing
- total: $0.042
Available Parameters
- audio: Audio URL (5-20 seconds) for lip sync
- resolution: Output video resolution (Options: 480p, 720p, 1080p)
- seed: Random seed for reproducibility
Quick Reference
To use this model, set: "model": "lightricks/ltx-23-lipsync"
Featured: No
Documentation: https://hinow.ai/models/lightricks/ltx-23-lipsync
API Endpoint: https://api.hinow.ai/v1
