ThinkyMachines 发布开源全模态模型 Inkling-Small，支持音频、文本和图像
英文摘要
ThinkyMachines has announced Inkling-Small, an open omni-modal model capable of processing audio, text, and image inputs. The model is described as a frontier open Omni. It is available to run on Inference Endpoints, simplifying deployment for developers. This release expands open access to multimodal AI models beyond text and image to include audio.
中文摘要
ThinkyMachines 发布了 Inkling-Small，一个开源的全模态模型，能够处理音频、文本和图像输入。该模型被描述为前沿的开源全模态模型。它可在推理端点（Inference Endpoints）上运行，简化了开发者的部署流程。此次发布将开放多模态 AI 模型的覆盖面从文本和图像扩展到了音频。
关键要点
ThinkyMachines released Inkling-Small, an open omni-modal model.
ThinkyMachines 发布了开源全模态模型 Inkling-Small。
The model supports audio, text, and image inputs.
该模型支持音频、文本和图像输入。
It is accessible via Inference Endpoints for easy deployment.
可通过推理端点轻松部署。