VideoUltra API
    Preparing search index...

    Interface OnDeviceTranscriberOptions

    interface OnDeviceTranscriberOptions {
        device?: "webgpu" | "wasm" | "auto";
        keepLoaded?: boolean;
        model?: CaptionModel | "auto";
        modelHost?: string;
        runtimePath?: string;
    }
    Index
    device?: "webgpu" | "wasm" | "auto"

    Runtime; default WebAssembly (as fast as WebGPU for these models, and lighter).

    keepLoaded?: boolean

    Keep the model loaded between jobs (faster next time, holds ~0.3–1 GB). Default false: the worker closes after each job and its memory goes back to the page; the downloaded files stay cached, so the next job only waits a few seconds.

    model?: CaptionModel | "auto"

    Model size; default picks for the device (see chooseModel).

    modelHost?: string

    Where model files come from — self-host them by mirroring the model repos: files are fetched from <modelHost>/onnx-community/whisper-<size>_timestamped/resolve/main/<file>. Default https://huggingface.co.

    runtimePath?: string

    Where the speech runtime's .wasm files are served (default: next to its JS module).