microsoft/VibeVoice

Open-Source Frontier Voice AI

Generative mediaPython

2.2 Steady Magnitude out of 10 — how fast interest is growing, not a quality score. Star growth looks organic. Data as of October 2, 2026, 13:20 UTC.

Open on Seismograph Open on GitHub

About the project

Microsoft's family of open-source voice AI models: ASR for speech recognition (up to 60 minutes of audio in a single pass with diarization and timestamps) and TTS for long multi-speaker dialogue synthesis. Streaming and edge variants included.

Useful for

Transcribe a one-hour meeting recording with speaker labels and timestamps
Set up streaming speech recognition with custom hotwords for domain terms
Generate a multi-speaker podcast or dialogue up to 90 minutes long

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

6 stars so far today, about 16 expected by the end of the day.
Over the last two days the pace is 1.7× that of the previous week and a half.
GitHub Trending Python today: #13, +36 stars.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 54,607
Today: 6 · ≈ 16 by evening
Forks: 6,147
Issues and pull requests: 430
Watchers: 269
Language: Python
License: MIT
Created: August 25, 2025
Last push: September 3, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Spotted in

October 2, 2026GitHub Trending Python today: #13, +36 stars

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/microsoft/VibeVoice.svg?lang=en)](https://gitnova.dev/en/r/microsoft/VibeVoice)

Similar by description

2.5
OpenWhispr/openwhispr
Cross-platform desktop voice-to-text dictation app that transcribes speech locally (Whisper, NVIDIA Parakeet) or in the cloud and pastes text into any app. It also transcribes meetings, manages notes, and connects to…

SteadyProductivity & self-hostedJavaScript+14 stars today, ≈ 28 by evening
1.5
jankeesvw/omarchy-meeting-recorder
Records meetings on Omarchy: mic and system audio as separate tracks, transcribed locally with whisper.cpp, with speaker labels, chapters and a player.

CoolingProductivity & self-hostedRust+2 stars today, ≈ 3 by evening
1.5
k2-fsa/sherpa-onnx
A collection of offline speech processing tools built on next-gen Kaldi and onnxruntime: speech recognition and synthesis, speaker diarization and identification, VAD, speech enhancement, source separation, and keyword…

SteadyLanguage modelsC+++3 stars today, ≈ 6 by evening
1.3
nobodywho-ooo/nobodywho
A Rust inference engine for running LLMs locally with bindings for Python, Kotlin, Swift, Flutter, React Native and Godot, plus speech-to-text and text-to-speech. It runs GGUF chat models offline on desktop and mobile…

CoolingLanguage modelsRust+0 stars today, ≈ 1 by evening
2.5
Zackriya-Solutions/meetily
A local AI meeting assistant that records and transcribes audio in real time using Whisper/Parakeet and generates summaries via Ollama or other LLMs, without sending data to the cloud.

SteadyAI agentsRust+15 stars today, ≈ 31 by evening
1.6
0xShug0/audio.cpp
A native C++ inference engine for audio models built on ggml: TTS, speech recognition, VAD, voice cloning, music generation. Runs without Python on CPU, CUDA, ROCm, Vulkan and Metal.

SteadyGenerative mediaC+++6 stars today, ≈ 12 by evening