wavespeed/infinitetalk

1---2title: InfiniteTalk3emoji: 🎬4colorFrom: indigo5colorTo: blue6sdk: docker7pinned: false8license: mit9short_description: Drive a portrait from an audio track — lip sync and head...10tags:11  - image-to-video12  - wavespeed13  - infinitetalk14  - lip-sync15  - talking-head16  - audio-driven17models:18  - MeiGen-AI/InfiniteTalk19---20 21# InfiniteTalk22 23Drive a portrait from an audio track — lip sync and head motion.24 25Runs [`wavespeed-ai/infinitetalk`](https://wavespeed.ai/models/wavespeed-ai/infinitetalk) through the26[WaveSpeed](https://wavespeed.ai) v3 API.27 28Upstream weights: [`MeiGen-AI/InfiniteTalk`](https://huggingface.co/MeiGen-AI/InfiniteTalk).29 30 31## Bring your own API key32 33This Space does not ship an API key. Paste your own in the field at the top —34create one in the [WaveSpeed dashboard](https://wavespeed.ai/dashboard).35 36Your key is sent only to `api.wavespeed.ai` to run the model. It is not stored,37not logged, and not written to disk. It is masked in the browser, stripped out38of error messages before they are displayed, and the generate event is marked39private so it never appears on Gradio's public API page — which would otherwise40publish client snippets containing every input, the key among them.41Generations are billed to your own account.42 43## Development44 45Source of truth is `_shared/` in the working repo, not this copy:46 47    python3 _shared/build_apps.py48