lipsync AI Models

sync/lipsync-2

Synchronizes lip movements in video to match input audio, creating realistic lipsync output. Uses a zero-shot approach r...

lipsync • 40.2K runs

zsxkib/multitalk

Generate conversational talking‑head videos from a reference image and one or two audio tracks. Provide an image with on...

🖼️ → 🎥 • lipsync • image-to-video-with-audio • audio-to-video • 2.3K runs

🤖 Model 🔊

emiliacb/rhubarb

Extract lip-sync mouth cues from speech audio and return time-aligned JSON for animation. Accepts common audio formats (...

🔊 • lip-sync-analysis • viseme-extraction • audio-analysis • 509 runs

stefan-st/face-diffuser

Generate lip-synced talking-head video from speech audio. Animate a preset face identity (F1–F8, M1–M6) with an optional...

🎥 • audio-to-video • lipsync • 205 runs

tmappdev/lipsync

Lipsync videos by matching a person’s mouth movements in an input video to a separate speech audio track. Accepts a vide...

lipsync • 6.9K runs

yuanxunlu/livespeechportraits

Generate lip-synced talking-head videos from an input audio clip. Provide a driving audio file (only the first 20 second...

🎥 • lipsync • audio-to-video • 9.8K runs

google/veo-3

Generates videos with synchronized audio from text prompts. Produces cinematic quality videos with realistic physics sim...

📝 → 🎥 • text-to-video-with-audio • image-to-video-with-audio • lipsync • 235.6K runs

lagune870601/sonic_cc

Synchronize a portrait image to input audio to create a talking head video. Accepts a single face image and a voice trac...

lipsync • 134 runs

wan-video/wan-2.5-t2v

Generate videos with synchronized audio from text prompts using Alibaba's WAN 2.5 model. Creates fully synchronized vide...

📝 → 🎥 • text-to-video-with-audio • lipsync • multilingual • 35.7K runs

bytedance/omni-human-1.5

Generates realistic videos from a single input image and audio clip, with optional text prompts for precise control. Pro...

🖼️ → 🎥 • image-to-video • audio-to-video • lipsync • 41.7K runs

andreasjansson/baby-in-a-corner

Add a lipsynced avatar overlay to a video. Provide an input video (up to 5 minutes, with audio) and an avatar image; the...

🎥 • lipsync • video-editing • 1 runs

zedge/live-portrait

Animate an animal photo into a talking or singing video. Provide a source image (animal) and drive it with a video, a mo...

🖼️ → 🎥 • image-to-video-with-audio • lipsync • 171.7K runs

zf-kbot/sonic

Generate lip-synced talking head videos from a single portrait image and an audio clip. Input a face image and speech au...

lipsync • talking-head • 104.7K runs

bytedance/seedance-1.5-pro

Generates videos with synchronized audio from text prompts, creating cinema-quality content with precise lip-syncing and...

📝 → 🎥 • text-to-video-with-audio • image-to-video-with-audio • lipsync • 2.8M runs

veed/fabric-1.0

Generate lip-synced talking-head videos from an input image and voice audio. Animate a single face image to speak the pr...

lipsync • talking-head • 4.2K runs

lightricks/audio-to-video

Generates videos from audio input using Lightricks's LTX-2 system, where the audio drives timing, motion, and performanc...

🎥 • audio-to-video • lipsync • 2.2K runs

wan-video/wan-2.6-i2v

Generates videos with synchronized audio from an input image and text prompt. Supports durations of 5-15 seconds at 720p...

🖼️ → 🎥 • image-to-video-with-audio • lipsync • 40.8K runs

heygen/avatar-iv

Generate talking-head avatar videos with audio from text input. Provide an avatar_id (supports public avatars, digital t...

📝 → 🎥 • text-to-video-with-audio • lipsync • talking-avatar • 1 runs