XimilalaXiang/DeLive — System audio capture + multi-provider ASR + local-first AI review workspace.

Description and use

XimilalaXiang/DeLive is an open‑source workspace that captures system audio and provides real‑time floating captions using 12 ASR backends covering more than 60 languages, while keeping all processing local‑first. It integrates AI capabilities for summarisation, chat, mind‑mapping, and custom agent skills via an Open API and an MCP server, offering both front‑end and back‑end components for a versatile, multi‑provider speech‑to‑text and AI review platform.

Problem

XimilalaXiang/DeLive helps turn media editing, captions, rendering, and transcoding into repeatable workflows.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• automate editing and rendering
• generate subtitles or dubbing
• build repeatable media-processing pipelines

Evidence

System audio capture + multi-provider ASR + local-first AI review workspace. Floating live captions, 12 ASR backends, 60+ languages, AI summary/chat/mindmap, Open API, MCP server, and Agent Skill.

Source