digital-human
LTX-2 Lipsync generates synchronized talking head videos from a reference image and audio input. Powered by the 19B DiT architecture, it produces high-fidelity lip-synced videos with natural head movements. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
Tu solicitud costará $0.1 por ejecución.
Con $1 puedes ejecutar este modelo aproximadamente 10 veces.
EjemplosVer todo
README
LTX-2 19B Lipsync
LTX-2 Lipsync is an audio-driven digital human model that generates synchronized talking head videos from a reference image and audio input. Powered by the 19B-parameter DiT (Diffusion Transformer) architecture, it produces high-fidelity lip-synced videos with natural head movements and expressions.
Why Choose This?
-
Audio-driven generation Simply provide an audio file and optional reference image — the model handles lip-sync, head motion, and expressions automatically.
-
High-fidelity output Leverages the 19B-parameter LTX-2 architecture for detailed, temporally consistent video with natural mouth movements.
-
Flexible resolution Supports 480p, 720p, and 1080p outputs to balance quality and cost.
-
Variable duration Video length is automatically determined by audio duration (5-20 seconds max).
Parameters
| Parameter | Required | Description |
|---|---|---|
| audio | Yes | Audio file URL for lip-sync (determines video length) |
| image | No | Reference portrait image (JPG or PNG) |
| prompt | No | Optional text to guide generation style |
| resolution | No | Output resolution: 480p, 720p (default), or 1080p |
| seed | No | Random seed for reproducibility (-1 for random) |
Resolution Options
| Resolution | Best For |
|---|---|
| 480p | Fast previews, iteration, lowest cost |
| 720p | Balanced quality and cost (default) |
| 1080p | Final delivery, maximum detail |
How to Use
- Upload your audio — the audio file that drives lip-sync and determines video duration.
- Upload your image (optional) — the reference portrait that defines the speaker's appearance.
- Write your prompt (optional) — describe any style or motion preferences.
- Select resolution — 480p for iteration, 720p for balance, 1080p for final output.
- Run — submit and download the lip-synced video.
Pricing
| Resolution | 5s | 10s | 15s | 20s |
|---|---|---|---|---|
| 480p | $0.075 | $0.15 | $0.225 | $0.30 |
| 720p | $0.10 | $0.20 | $0.30 | $0.40 |
| 1080p | $0.15 | $0.30 | $0.45 | $0.60 |
Billing Rules
- Base price: $0.10 (720p, 5 seconds)
- Duration: Determined by audio length (min 5s, max 20s billing)
- Resolution multiplier: 480p = 0.75×, 720p = 1×, 1080p = 1.5×
- Total cost = duration × $0.10 × resolution_multiplier / 5
Best Use Cases
- Digital Avatars — Create talking head videos for virtual presenters and avatars.
- Content Creation — Generate lip-synced videos for social media and marketing.
- Localization — Dub existing content with new audio while maintaining visual consistency.
- Accessibility — Create sign language or narrated content with synchronized visuals.
- Education — Produce instructional videos with talking head presenters.
Pro Tips
- Use clear, high-quality audio for best lip-sync results.
- Provide a front-facing portrait image with visible mouth for optimal generation.
- Use high-quality, sharp, well-lit portrait images for best results.
- Iterate at 480p to dial in results, then render at higher resolution for final output.
- Use fixed seed when comparing variations to isolate changes.
Notes
- Maximum video duration is 20 seconds (determined by audio length).
- Audio longer than 20 seconds will be truncated.
- The aspect ratio of output video is influenced by your input image.
Related Models
- LTX-2 19B Image-to-Video — Animate images with synchronized audio from text prompts.
- LTX-2 19B Text-to-Video — Generate video with audio from text only.
- InfiniteTalk — Alternative audio-driven talking head generation.