voice-assistant

Convert Arabic audio to text and generate spoken responses using Whisper and TTS.

13|4|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/Moshe-ship/hurmoz --skill voice-assistant-moshe-ship
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: voice-assistant
Source: https://github.com/Moshe-ship/hurmoz/tree/main/voice-assistant
Command: npx skills add https://github.com/Moshe-ship/hurmoz --skill voice-assistant-moshe-ship

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

مساعد صوتي عربي يتيح تحويل الكلام المنطوق إلى نص، ثم معالجته وتوليد رد صوتي بالعربية ليتيح تواصلاً صوتياً كاملاً من خلال خط أنابيب متكامل.

Core Features & Use Cases

  • تحويل الكلام إلى نص باستخدام Whisper مع دعم العربية لاستخراج نص دقيق
  • معالجة النص عبر نموذج لغوي لإنتاج ردود واقعية ومتجاوبة
  • تحويل الرد إلى صوت باستخدام تقنيات TTS بدعم العربية، مع خيارات صوتية ووضوح
  • تطبيقات محتملة: مساعدات صوتية شخصية، خدمات العملاء الذكية، والتفاعل الصوتي للمحتوى التعليمي

Quick Start

ابدأ بتشغيل خط الأنابيب على ملف صوتي مثل sample.wav لتحويله إلى نص ثم إصدار رد صوتي.

Frequently Asked Questions about voice-assistant

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

FAQPage Schema
How do I convert Arabic speech to text and generate a spoken response?

An Arabic voice assistant converts spoken Arabic audio to text using Whisper, processes it through an LLM to generate contextual responses, and outputs spoken Arabic replies via TTS for full voice conversations.

Can I use Whisper for Arabic speech-to-text transcription?

Yes, Whisper handles Arabic speech-to-text transcription within this voice assistant pipeline, extracting accurate text from spoken Arabic audio files before passing it to the LLM for processing.

Does this voice assistant pipeline support full Arabic text-to-speech output?

Yes, the pipeline includes text-to-speech output using TTS technologies to convert LLM-generated text responses into clear spoken Arabic with selectable voice options and clarity settings.

What's the best way to build an interactive Arabic voice assistant?

Building an interactive Arabic voice assistant requires an end-to-end pipeline integrating Whisper for STT, an LLM for contextual reasoning, and TTS for generating natural spoken Arabic responses.

Do I need an audio file to start the Arabic speech-to-text and TTS pipeline?

Yes, you need an audio file like sample.wav to start the pipeline, which preprocesses the audio, transcribes Arabic speech via Whisper, generates an LLM response, and outputs spoken Arabic.