video-to-video
Sync React-1 is a production-grade video-to-video lip-sync model. It maps any speech track to a target face, producing phoneme-accurate visemes and smooth timing while preserving identity, head pose, lighting, and background. Supports emotion and intensity control, multilingual speech, and long takes for talking-head content. Built for stable production use with a ready-to-use REST API, no cold starts, and predictable pricing.
Idle
Your request will cost $0.835 per run.
For $10 you can run this model approximately 11 times.
One more thing::
ExamplesView all
README
sync/react-1 (Audio-to-Video Lip Sync & Facial Animation)
sync/react-1 is a production-ready audio-driven video animation model that syncs a subject in a video to an input audio track. It supports selectable emotion control and multiple animation modes (lips / face / head) to help you generate natural, expressive results for short clips with minimal setup.
Why it stands out
- Audio-to-video sync for fast talking-head and reaction style outputs.
- Emotion presets (happy / sad / angry / disgusted / surprised / neutral) to steer overall expression.
- Multiple control modes so you can animate only lips, or drive broader face/head motion.
- Simple workflow and predictable pricing for quick iteration.
Capabilities
-
Audio-driven lip sync for an input video
-
Emotion-conditioned expression steering
-
Mode control for different animation scopes:
- lips: focus on mouth movement
- face: include facial expression changes
- head: include head motion cues (where supported by the model)
Parameters
| Parameter | Description |
|---|---|
| video* | Input video file or public URL. |
| audio* | Input audio file or public URL. |
| emotion | Expression preset: happy / sad / angry / disgusted / surprised / neutral. |
| model_mode | Animation scope: lips / face / head. |
Pricing
| Video Duration (s) | Total Price |
|---|---|
| 1 | $0.167 |
| 2 | $0.334 |
| 3 | $0.501 |
| 4 | $0.668 |
| 5 | $0.835 |
How to use
- Upload the video (best with a clear, front-facing subject).
- Upload the audio (speech, voiceover, or short dialogue).
- Choose emotion to steer expression tone.
- Choose model_mode (lips / face / head).
- Run the model and download the synced result.
Best Use Cases
- Short talking-head clips for creators and social media
- Dubbing and voiceover sync for character shots
- Expressive reaction clips with controlled emotion
- Rapid prototyping for dialogue-driven video concepts
Notes
- Best results: single subject, stable lighting, minimal motion blur, and a visible face.
- Use lips mode for the most conservative edits; use face/head when you want stronger performance and expression.
- Very long videos are billed at the 5-second cap, so trim to the segment you want to animate.
More Digital Human Models
-
wavespeed-ai/infinitetalk — Create realistic talking-head digital humans from a single portrait and audio, delivering stable lip sync and natural facial motion for voice-driven avatar videos.
-
wavespeed-ai/infinitetalk/multi — Multi-person talking avatar generation that syncs multiple faces to audio with consistent expressions and timing, ideal for dialogues, interviews, and group scenes.
-
kwaivgi/kling-v2-ai-avatar-pro — Pro-grade AI avatar video generation for high-fidelity digital humans with strong identity consistency and polished, production-ready results for marketing and creator content.