How do I install the Vibevoice skill?

Run npx skillmds@latest add fikriaf/vibevoice in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Vibevoice safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Vibevoice?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Vibevoice free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Vibevoice?

fikriaf (@fikriaf) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Vibevoice by fikriaf — Agent Skill

Name: Vibevoice
Author: fikriaf

File contents

VibeVoice

Microsoft open-source frontier Voice AI from https://github.com/microsoft/VibeVoice (44k stars)

Models

Model	Description	Quick Try
VibeVoice-ASR-7B	Speech-to-text, 60-min audio, speaker diarization	Playground
VibeVoice-TTS-1.5B	Text-to-speech (disabled)	N/A
VibeVoice-Realtime-0.5B	Real-time streaming TTS	Colab

Key Features

VibeVoice-ASR

60-minute single-pass — Processes long audio without chunking
Rich transcription — Who (Speaker), When (Timestamps), What (Content)
Multilingual — 50+ languages supported
Custom hotwords — Domain-specific terminology support
Hugging Face Transformers — Native HF integration

VibeVoice-Realtime

Streaming text input — Real-time TTS
Multilingual voices — DE, FR, IT, JP, KR, NL, PL, PT, ES
11 English styles — Different voice characteristics

Installation

# Clone
git clone https://github.com/microsoft/VibeVoice
cd VibeVoice

# Install
pip install -e .

Usage

ASR (Speech Recognition)

from transformers import pipeline

asr = pipeline(
    "automatic-speech-recognition",
    model="microsoft/VibeVoice-ASR"
)
result = asr("audio_file.wav")
print(result["text"])

Fine-tuning ASR

cd finetuning-asr
# See finetuning-asr/README.md for details

vLLM Inference (Faster)

# See docs/vibevoice-vllm-asr.md

Requirements

Python 3.8+
PyTorch
GPU recommended for inference
Transformers library

Resources

Location

Installed at: /opt/VibeVoice

---name: vibevoicedescription: Microsoft open-source frontier Voice AI — ASR (speech-to-text) and TTS (text-to-speech). Handles 60-min audio, multilingual, speaker diarization.---# VibeVoiceMicrosoft open-source frontier Voice AI from https://github.com/microsoft/VibeVoice (44k stars)## Models| Model | Description | Quick Try ||-------|-------------|-----------|| VibeVoice-ASR-7B | Speech-to-text, 60-min audio, speaker diarization | [Playground](https://aka.ms/vibevoice-asr) || VibeVoice-TTS-1.5B | Text-to-speech (disabled) | N/A || VibeVoice-Realtime-0.5B | Real-time streaming TTS | [Colab](https://colab.research.google.com/github/microsoft/VibeVoice/blob/main/demo/vibevoice_realtime_colab.ipynb) |## Key Features### VibeVoice-ASR- **60-minute single-pass** — Processes long audio without chunking- **Rich transcription** — Who (Speaker), When (Timestamps), What (Content)- **Multilingual** — 50+ languages supported- **Custom hotwords** — Domain-specific terminology support- **Hugging Face Transformers** — Native HF integration### VibeVoice-Realtime- **Streaming text input** — Real-time TTS- **Multilingual voices** — DE, FR, IT, JP, KR, NL, PL, PT, ES- **11 English styles** — Different voice characteristics## Installation```bash# Clonegit clone https://github.com/microsoft/VibeVoicecd VibeVoice# Installpip install -e .```## Usage### ASR (Speech Recognition)```pythonfrom transformers import pipelineasr = pipeline( "automatic-speech-recognition", model="microsoft/VibeVoice-ASR")result = asr("audio_file.wav")print(result["text"])```### Fine-tuning ASR```bashcd finetuning-asr# See finetuning-asr/README.md for details```### vLLM Inference (Faster)```bash# See docs/vibevoice-vllm-asr.md```## Requirements- Python 3.8+- PyTorch- GPU recommended for inference- Transformers library## Resources- [Documentation](docs/vibevoice-asr.md)- [Hugging Face](https://huggingface.co/microsoft/VibeVoice-ASR)- [ASR Paper](https://arxiv.org/pdf/2601.18184)- [TTS Paper](https://openreview.net/pdf?id=FihSkzyxdv)## LocationInstalled at: /opt/VibeVoice

Frequently asked questions

Vibevoice