KDTalker_gradio_infer – 1 MCP server offers this tool
What it usually takes
driven_audio– in 1 of 1source_image– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
KDTalker co.huggingface.fffiloni/kdtalker Generate a talking-head video from a static source image and an audio file. This function uses a pre-trained motion and lip-sync model to animate a face image so that it appears to speak in sync with a given audio clip. The resulting video is saved and returned. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: A file path to the generated .mp4 video, which shows the input face animated, to speak and move in sync with the audio., Workflow:, 1. Load and initialize the animation pipeline (Inferencer)., 2. Process the image and audio., 3. Generate a talking-head animation using lip-sync and motion synthesis models., 4. Combine generated video frames with the original audio., 5. Return the video path to be displayed or downloaded. | driven_audio,source_image | Not stated |