OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Delive

Delive is an open-source desktop transcription workspace that captures system audio or accepts audio and video files, routes them through multiple ASR providers, and provides tools to search and review transcripts.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Delive — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Delive when transcription needs to happen in a desktop workspace and you want to continue from capture or file transcription into searchable history and AI-assisted review.

Who it is for

  • People who want captions or transcripts from meetings, lectures, streams, courses, podcasts or other computer playback.
  • Users who need to transcribe an existing audio or video file and revisit the result.
  • Developers or AI-tool users seeking documented Open API, WebSocket or MCP integration routes.

Documented uses

  • Capture computer playback and produce live captions or a transcript.
  • Transcribe an audio or video file with a supported ASR provider.
  • Search transcript history and organize sessions with tags or topics.
  • Correct, summarize, question or map transcript content in the AI Review Desk.
Before you choose

Requirements & limits

The repository lists desktop releases for Windows, macOS and Linux. Delive is open source under the Apache-2.0 license.

  • Cloud and local ASR options are both listed; supported features differ by provider.
  • The application documents system-audio capture and audio/video file transcription, but some newer features are identified as prerelease or source-build options.
  • An always-on-top caption overlay offers source, translated and dual display modes.
  • The repository documents a local REST API, real-time WebSocket and MCP server.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up DeLive for live audio transcription

Install DeLive, configure an ASR provider, and begin recording audio from a selected screen or window.

Before you start

  • A supported Windows, macOS, or Linux system (Linux requires PulseAudio loopback support).
  • At least one ASR provider configured with its required API key or a local service.

Steps

  1. Download the release for your platform from the GitHub Releases page and open DeLive.

  2. On first launch, open Settings and select an ASR backend from the Service tab.

  3. Enter the required API key or configure a local service, then use Test Config to verify connectivity.

  4. Go to Live, click Start Recording, and select a screen or window with audio sharing enabled.

Expected outcome

DeLive is configured with an ASR backend and starts recording audio from the selected screen or window for transcription.

Guide limitations

  • The workflow requires at least one configured ASR provider.
  • Windows may show a SmartScreen warning on first launch; the getting-started guide says to choose More info → Run anyway for this unsigned app.
  • Linux requires PulseAudio loopback support.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
XimilalaXiang/DeLive · Official homepage title · retained in its source language
How we review sourcesSuggest a correction