CapCut

Earshot is an open-source toolkit that gives coding agents practical access to audio understanding and sound creation. It ships as a command-line tool, Python API, and Model Context Protocol server, allowing compatible agents to inspect recordings, search for relevant moments, compare audio against text, and generate or fit procedural sound recipes. Developers building audio, video, or creative applications can use it to make sound part of an agent workflow instead of relying only on transcripts or external hosted services. Earshot is designed to run locally on CPU, which keeps media private and avoids per-request cloud inference, though its documented models require a substantial initial download. Its recent launch visibility reflects growing demand for multimodal agents that can work with sound as well as code and text.

Desert Ant Labs provides a family of small, specialized AI models and native SDKs designed to run on-device instead of through metered cloud inference. Its product line includes Voz for speech recognition, Clear for audio enhancement, Redact for privacy filtering, Clips for selecting video highlights, and other focused models that can be embedded into apps with Swift, Kotlin, or JavaScript. Voz is a concrete example: it transcribes 25 languages with word-level timestamps, runs on Apple platforms, and can process long audio locally with no login or per-token bill. The service is aimed at mobile and desktop developers building private, responsive AI features into their own products. Its official site offers free usage up to 100,000 monthly active devices per platform, while documentation and Hugging Face model pages provide installable evidence. This is an SDK/model platform, not merely a research announcement.

Livepeer Agent is an early-access platform that turns any agent harness into a production video studio by bringing image, video, audio, 3D, editing, rendering, and compositing tools directly into agent workflows. Instead of agents stopping at text or code, they can generate and manipulate rich media as part of a task, with Livepeer's GPU infrastructure handling the heavy lifting. It targets developers and creative-tool builders who want agents that produce finished video assets, not just descriptions of them. Livepeer Agent is notable now because multimodal agent pipelines are expanding beyond language into real media production, and video generation is becoming a callable primitive rather than a separate app. Currently in early access, it positions Livepeer's streaming heritage as agent-facing creative infrastructure.