Menu
Microsoft open-source frontier Voice AI — ASR (speech-to-text) and TTS (text-to-speech). Handles 60-min audio, multilingual, speaker diarization.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
AgentOS CLI - Autonomous agent framework with ROMA planning, HTAA tool grouping, MOSAIC safety, InfiAgent memory, and REDEREF reflection. Use for complex task automation.
Safely handle requests to install all Kali tools on Ubuntu/Debian hosts; detect incompatibility, avoid breaking base system, rollback repo changes, and pivot to container/chroot/VM strategy.
Bring up OpenClaw Telegram channel and debug "bot online but not replying" by separating channel transport issues from LLM/auth issues.
Deploy Supabase self-hosted on Ubuntu with Docker, handle Compose package quirks, initialize secure .env, bring up stack, and verify DB connectivity for app use.
Systematic exploratory QA testing of web applications — find bugs, capture evidence, and generate structured reports
Direct browser control via CDP (Chrome DevTools Protocol). Connects to the user's already-running Chrome for automation, scraping, testing, and web interaction.
| name | vibevoice |
| description | Microsoft open-source frontier Voice AI — ASR (speech-to-text) and TTS (text-to-speech). Handles 60-min audio, multilingual, speaker diarization. |
Microsoft open-source frontier Voice AI from https://github.com/microsoft/VibeVoice (44k stars)
| 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 |
# Clone
git clone https://github.com/microsoft/VibeVoice
cd VibeVoice
# Install
pip install -e .
from transformers import pipeline
asr = pipeline(
"automatic-speech-recognition",
model="microsoft/VibeVoice-ASR"
)
result = asr("audio_file.wav")
print(result["text"])
cd finetuning-asr
# See finetuning-asr/README.md for details
# See docs/vibevoice-vllm-asr.md
Installed at: /opt/VibeVoice