AI Agent Skills

Build local voice agents with open-source models

Plan a practical long-form video with test prompts, recording structure, narration beats, screen-recording steps, and production handoff.

Build a reproducible local rough-cut workflow for talking-head or narrated screen-recording videos with transcript review gates.

Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

Generate topic-first, two-part video-title candidates from an approved video brief or final script.

Generate real-timestamp subtitle artifacts from final narration audio or merged video with a caption quality gate.