baidu-speech-to-text

Converts ogg/opus voice messages to text via Baidu Speech Recognition API.

18|1|Updated Jan 29, 2026

Search Tags:#speech recognition #transcription #china #voice to text #baidu ai #proxy bypass

Ready to run

npx skills add https://github.com/castle-x/skills-x --skill baidu-speech-to-text

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: baidu-speech-to-text
Source: https://github.com/castle-x/skills-x/tree/main/skills/baidu-speech-to-text
Command: npx skills add https://github.com/castle-x/skills-x --skill baidu-speech-to-text

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill converts voice messages (ogg/opus) into text, specifically optimized for domestic Chinese servers and proxy environments, overcoming common connectivity issues with Baidu's API.

Core Features & Use Cases

Voice-to-Text Conversion: Accurately transcribes audio files into text.
Multi-Language Support: Supports Mandarin, English, Cantonese, and Sichuan dialect.
Proxy Bypass: Automatically bypasses proxy settings to ensure direct access to Baidu's API from within China.
Use Case: Automatically transcribe voice messages received on platforms like Discord or WhatsApp when your server is located in China and uses a proxy.

Quick Start

Convert the audio file located at '/path/to/your/voice.ogg' to text using the default Mandarin language.

Frequently Asked Questions about baidu-speech-to-text

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

FAQPage Schema

How do I transcribe Discord or WhatsApp voice messages to text on a server in China?▼

To transcribe voice messages to text on a server in China, this Skill converts ogg/opus audio files via the Baidu Speech Recognition API. It automatically bypasses proxy settings to ensure direct API access from domestic Chinese network environments.

Does Baidu speech recognition work behind a proxy environment?▼

Baidu speech recognition works behind a proxy environment by automatically bypassing proxy settings during execution. This ensures direct, uninterrupted API access for transcribing your ogg/opus voice messages from within China.

Can I transcribe Cantonese or Sichuan dialect voice messages to text?▼

You can transcribe Cantonese or Sichuan dialect voice messages to text using this Skill. It supports multi-language recognition including Mandarin, English, Cantonese, and Sichuan dialect via the Baidu Speech Recognition API.

Do I need ffmpeg to convert ogg voice files to text?▼

Yes, you need ffmpeg installed to convert ogg/opus voice files to text. It acts as a required dependency for processing the audio files before sending them to the Baidu Speech Recognition API for transcription.

What is the best way to convert opus audio files to text for domestic Chinese users?▼

The best way to convert opus audio files to text for domestic Chinese users is using a Skill optimized for local servers. This solution directly calls the Baidu Speech Recognition API, automatically handling proxy bypass for stable domestic connectivity.

Why does my voice to text transcription fail when using a proxy in China?▼

Voice to text transcription may fail when a proxy interferes with domestic API connections. This Skill solves the issue by automatically bypassing proxy settings to establish a direct connection with the Baidu Speech Recognition API servers.