voice

Transcribes audio files to text and synthesizes expressive speech in multiple languages.

1|Updated Apr 13, 2026

Search Tags:#text-to-speech #speech recognition #audio processing #voice cloning #model management

Ready to run

npx skills add https://github.com/cnbison/lbc-skills --skill voice-cnbison

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: voice
Source: https://github.com/cnbison/lbc-skills/tree/main/skills/mofa-fm/.octos/platform-skills/voice
Command: npx skills add https://github.com/cnbison/lbc-skills --skill voice-cnbison

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ominix-api, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Converts spoken language into text and synthesizes speech from text with emotional tone, enabling natural voice interactions on Apple Silicon devices.

Core Features & Use Cases

Speech Recognition: Transcribes audio files into text, supporting multiple languages including Chinese, English, Japanese, and Korean.
Text-to-Speech: Generates speech audio from text with preset voices and emotion prompts to produce expressive speech.
Model Management: Allows downloading and managing different voice models for customized performance.
Use Case: Create a voice assistant that transcribes user speech and responds with emotion-aware speech synthesis in a specific language.

Quick Start

Transcribe an audio file named 'sample_audio.wav' into text and synthesize it with a cheerful voice.

Frequently Asked Questions about voice

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

FAQPage Schema

How do I transcribe an audio file into text with expressive text-to-speech?▼

Speech recognition transcribes audio files into text by processing spoken language through local models. It supports multiple languages including Chinese, English, Japanese, and Korean for accurate transcription.

Can I clone a voice and manage models for text-to-speech synthesis?▼

Yes, voice cloning and model management allow downloading and managing different voice models for customized performance. You can synthesize speech from text using preset voices and emotion prompts.

Do I need an ominix-api server to run speech recognition and voice synthesis?▼

Yes, you need an ominix-api server and local models to operate speech recognition and voice synthesis. The Skill runs real-time speech-to-text and text-to-speech processing directly on device.

Does text-to-speech support multiple languages for voice applications?▼

Text-to-speech supports multiple languages including Chinese, English, Japanese, and Korean for interactive voice applications. It generates speech audio from text with preset voices and emotion prompts.

What is the best way to create a voice assistant with emotion-aware speech?▼

Combine speech recognition to transcribe user speech with text-to-speech to respond with emotion-aware speech synthesis in a specific language. This creates a natural voice assistant for interactive applications.