--- title: "Kling LipSync AI Lip Sync | Made" description: "Sync any talking video to a new audio track with Kling LipSync in Made. See original examples, per-second pricing, and limits. On Made: 0.14 credits / second." url: https://www.made.app/models/kling-lipsync --- [Models](https://www.made.app/models) / Kling LipSync Kling AI · video model # Kling LipSync Re-voice any video 0.14 credits / second · every plan · [price breakdown](https://www.made.app/price-sheet/kling-lipsync) · [API playground](https://www.made.app/playground/kling-lipsync) [Upload a video and audio](https://www.made.app/tools/ai-video-generator?model=kling-lipsync) Add a video of a person and the audio it should speak — no prompt needed. Made with Kling LipSync · Re-voiced to a new track Kling LipSync takes a video of a person and a new audio track and regenerates realistic lip movement to match — swap the script, the language, or the voice without reshooting a frame. Original results ## Kling LipSync examples made in Made These examples use media produced for Made. Prompts are included when the production record allows them. ### Re-voiced to a new track ### The original take ### Second clip, different voice ### The original second take Input ![Frame from the original take](https://www.made.app/images/models/kling-lipsync/dialogue-frame-before.jpg) Output ![The same frame with the mouth regenerated to match the new audio](https://www.made.app/images/models/kling-lipsync/dialogue-frame-after.jpg) ### Same frame, new mouth shape Input ![Frame from the original second take](https://www.made.app/images/models/kling-lipsync/closing-frame-before.jpg) Output ![The same frame of the second clip re-synced to the new track](https://www.made.app/images/models/kling-lipsync/closing-frame-after.jpg) ### Second clip, same frame ## Where Kling LipSync fits best ### Best uses - Re-voicing UGC and creator footage with a new script - Dubbing a clip into another language with matching mouth movement - Fixing flubbed lines without reshooting - Localizing one performance across many voice tracks ### Limits to know - Billing follows input video length at 0.14 credits a second in started 5-second increments — a 3-second clip bills as 5 seconds. - It needs a clearly visible face; profiles, occlusions, and multiple speakers degrade the sync. ## Specifications in Made These are the controls exposed by Made, which may be narrower than a provider’s full API. **Aspect ratios** Matches the input video **Resolution** Matches the input video **Duration** Matches the input video **Output formats** MP4 **Reference images** 1 **Processing** Scales with clip length; progress appears in the generation view. ## How to use Kling LipSync in Made 1. **Add the video** Upload a clip with one clearly visible face — the rest of the frame is left untouched. 2. **Add the audio** Upload the track the person should speak: a new script, a translation, or a different voice. 3. **Check the quote** Billing follows the input video’s length in 5-second steps; Made shows the exact price first. 4. **Review the sync** Check mouth shapes against hard consonants; regenerate with cleaner audio if the sync drifts. Capabilities reviewed 2026-09-03 · Provider: [Kling AI](https://fal.ai/models/fal-ai/kling-video/lipsync/audio-to-video) Made shows the price in credits before generation. [View Made pricing](https://www.made.app/pricing) ## Go deeper on Kling LipSync ### [Kling LipSync pricing](https://www.made.app/price-sheet/kling-lipsync) 0.14 credits / second — the full breakdown, verified. ## Compare relevant models video ### [VEED Fabric 1.0](https://www.made.app/models/veed-fabric) VEED Fabric 1.0 animates a single photo to speak any audio track — face, mouth, and subtle head motion are generated to match the voice, producing a talking video as long as the audio. video ### [Happy Horse 1.1](https://www.made.app/models/happy-horse-1-1) Happy Horse 1.1 is Alibaba’s flagship video model — a long-running #1 on the Artificial Analysis Video Arena — generating 3 to 15 second clips at 1080p with native audio and multilingual lip-sync. video ### [Kling 3 Pro](https://www.made.app/models/kling-3-pro) Kling 3 Pro is the benchmark tier of Kling AI’s third-generation video model, generating 3 to 15 second clips with optional native audio and the cinematic motion the Kling line is known for. ## Continue with a related tool ### [AI Video Generator](https://www.made.app/ai-video-generator) Turn any image into a captivating video. Upload a photo, describe the motion you want, and watch AI bring it to life with realistic movement, cinematic camera work, and professional quality. ### [Image to Video Generator](https://www.made.app/image-to-video-generator) Upload a still photo, describe the motion or pick a suggestion, and MiniMax H3 Max animates it into a five-second MP4 clip with camera movement and subject motion. ### [AI Image Generator](https://www.made.app/ai-image-generator) Create scroll-stopping product photos and marketing visuals in seconds. Describe your shot, pick your style, and get professional images ready for your store, social feed, or ad campaign. Questions, answered ## Kling LipSync FAQ Need a specific answer? [Contact support](mailto:support@made.app) ### What is Kling LipSync? It is Kling AI’s audio-to-video lip-sync model: give it a video of a person and an audio track, and it regenerates the mouth region so the person convincingly speaks the new audio. ### How is it priced? By input video length: 0.14 credits a second, billed in started 5-second increments — a 5-second clip costs 1 credit (each job rounds up to a whole credit), and a 3-second clip bills the same. Made quotes the exact cost before generation. ### Does it need a prompt? No. The video and the audio track are the only inputs. ### Does it change anything besides the mouth? No — framing, motion, lighting, and identity stay from the source video; only the lip and jaw region is regenerated to match the audio. ### Can it dub into another language? Yes. The model syncs to whatever audio you provide, so a translated voice track produces matching mouth movement in that language. ### When should I choose another model? Choose VEED Fabric 1.0 when you only have a photo rather than a video, or Happy Horse 1.1 to generate a talking scene from scratch with its own voice. --- Markdown version of https://www.made.app/models/kling-lipsync. Every public Made page has one at its URL plus .md (https://www.made.app/models/kling-lipsync.md). Site summary for AI assistants: https://www.made.app/llms.txt