vibevoice

Transcribe speech to text with speaker diarization and multilingual support.

Updated Apr 29, 2026

Search Tags:#text-to-speech #speech recognition #audio transcription #multilingual support #AI voice processing

Ready to run

npx skills add https://github.com/fikriaf/agentos --skill vibevoice

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: vibevoice
Source: https://github.com/fikriaf/agentos/tree/main/src/agentos/skills/mlops/vibevoice
Command: npx skills add https://github.com/fikriaf/agentos --skill vibevoice

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires transformers, torch, and includes scripts (resource) components.

What problem does it solve?

VibeVoice addresses the need for efficient audio transcription and speech generation, enabling automated speech recognition (ASR) and text-to-speech (TTS) processing, which can save significant time and effort in handling voice data.

Core Features & Use Cases

ASR: Converts spoken words to text, supporting long audio files and speaker diarization.
TTS: Converts text to natural-sounding speech, though this function is currently disabled in the skill.
Use Case: Ideal for transcribing long meetings, automating customer service responses, or creating audiobooks from text documents.

Quick Start

Activate the vibevoice skill and provide the audio file for transcription, for example: "transcribe audio_file.wav".

Frequently Asked Questions about vibevoice

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I transcribe long audio files with speaker diarization using Python?▼

To transcribe long audio files with speaker diarization in Python, you can use this skill to process up to 60-minute recordings. It leverages PyTorch and Hugging Face Transformers to automatically convert spoken words into structured text.

Does automated speech recognition work with multilingual audio transcription?▼

Yes, automated speech recognition supports multilingual audio transcription. This skill can process audio files containing different languages, automatically converting the spoken words into accurate text using advanced AI models.

What is the best way to convert text to speech using AI voice processing?▼

Converting text to speech using AI voice processing typically involves generating natural-sounding audio from text documents. While this skill includes TTS functionality, note that the text-to-speech feature is currently disabled in its implementation.

Do I need PyTorch and Hugging Face Transformers to run audio transcription?▼

Yes, you need PyTorch and Hugging Face Transformers to run audio transcription with this skill. These frameworks provide the underlying neural network architecture required to process audio files and accurately execute speech recognition.

Can I transcribe a 60-minute meeting recording for automated speech recognition?▼

Yes, you can transcribe a 60-minute meeting recording for automated speech recognition. The skill explicitly supports long audio files up to 60 minutes, including speaker diarization to identify different speakers.