aliyun-tts

What This Skill Does

The aliyun-tts skill is a powerful integration for OpenClaw that enables high-quality, professional-grade text-to-speech synthesis using Alibaba Cloud's advanced AI infrastructure. By leveraging neural network-based voice models, this skill converts plain text into natural-sounding audio files. It is specifically designed to work within the OpenClaw ecosystem, allowing agents to generate vocal feedback, narration, or audio assets directly from the terminal or through automated workflows. The skill supports multiple voice profiles, flexible audio formats, and configurable sample rates, making it suitable for both casual experimentation and production-grade audio generation tasks.

Installation

To install this skill, use the ClawHub package manager. Run the following command in your terminal: clawhub install openclaw/skills/skills/guang384/aliyun-tts. After installation, you must configure your Alibaba Cloud credentials. You can perform this using the CLI command clawdbot skills config aliyun-tts for the ALIYUN_APP_KEY, ALIYUN_ACCESS_KEY_ID, and ALIYUN_ACCESS_KEY_SECRET. Alternatively, you can edit the configuration file located at ~/.clawdbot/clawdbot.json directly to input these credentials.

Use Cases

This skill is ideal for developers and content creators looking to enhance their automation tasks with audio output. Primary use cases include: 1) Creating audio narration for video tutorials or documentation. 2) Generating dynamic voice replies in chatbot applications, adding a personal touch to automated responses. 3) Building accessibility tools that convert text-heavy datasets or reports into audible summaries. 4) Automating the production of multilingual voiceovers for localized content.

Example Prompts

1. "Generate an mp3 file from this text: 'Welcome to your daily briefing, the current time is 9:00 AM', using the xiaoyun voice profile."
2. "Convert my latest report summary into an audio file saved at /tmp/summary.mp3 with a sample rate of 16000."
3. "Create a voice reply saying 'Action completed successfully' and provide the file path for me to use in my response."

Tips & Limitations

To ensure consistent quality, always verify that your Alibaba Cloud credentials have the appropriate TTS permissions enabled in the console. Note that generating high-quality audio files incurs usage costs according to Alibaba Cloud's pricing tier, so monitor your usage frequency. If you experience latency, experiment with different sample rates; 16000Hz is standard for most voice applications. Always check the official Alibaba Cloud documentation for an updated list of available voices if you require specific accents or gender tones beyond the common defaults.