← Discover
GitHub · microsoft/VibeVoice

Analyzing long audio recordings with artificial intelligence

Published by Microsoft, VibeVoice was developed as an open source voice AI framework. With its Python-based structure, the system allows users to train their own sound models and integrate them into their applications.

Updates

  • September 27, 2026: Stars 51,860 → 54,502.
  • August 2, 2026: Stars 48,569 → 51,860.

What you get

  • Converts up to 60 minutes of audio recording to text at a time.
  • It provides speaker ID, timestamp and content details in a structured way.
  • Provides user-defined keyword support for custom terms and names.

Installation

Install from GitHub
git clone https://github.com/microsoft/VibeVoice.git
cd VibeVoice
pip install -e .

Running it

Gradio demo
python demo/vibevoice_asr_gradio_demo.py --model_path microsoft/VibeVoice-ASR --share
Transcription from file
python demo/vibevoice_asr_inference_from_file.py --model_path microsoft/VibeVoice-ASR --audio_files [ses-dosyasi]

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to analyze the 60-minute audio recording I have using the VibeVoice model. I need to retrieve who the speakers are, when they spoke, and the content they said as a structured text file. I also want to add custom keywords so that the model recognizes technical terms more accurately, how can I structure this process?

Repository: https://github.com/microsoft/VibeVoice. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

Artificial Intelligence
Who it is forIt is suitable for users who want to quickly and structuredly convert long-term audio recordings, meeting summaries or podcast content into text.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-07: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.