SiliconFlow TTS Generation for Openclaw

A high-performance text-to-speech skill leveraging the SiliconFlow API and CosyVoice2 model for realistic voice synthesis.

lilei0311
v1.0.0
Feb 15, 2026
0
1.7k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install siliconflow-tts-gen

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install siliconflow-tts-gen using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is SiliconFlow TTS Generation?

The SiliconFlow TTS Generation skill enables developers to integrate advanced text-to-speech capabilities into their automated workflows using the SiliconFlow API. Built on the powerful CosyVoice2 model, it provides high-fidelity audio generation with an impressive 150ms first packet delay, making it ideal for real-time applications.

By leveraging Openclaw Skills like this one, users can access a curated selection of 8 preset male and female voices across multiple languages, including English, Japanese, and Korean. It also features specialized support for various Chinese dialects, ensuring that your generated speech sounds natural and localized for global audiences.

SiliconFlow TTS Generation Use Cases

  • Automated voiceover generation for marketing videos, social media content, or presentations.
  • Developing multilingual accessibility tools for web and mobile applications.
  • Creating localized audio content using specific Chinese dialects such as Cantonese, Sichuan, or Shanghai.
  • Rapidly prototyping voice-enabled AI agents and virtual assistants that require low-latency responses.

How SiliconFlow TTS Generation Works

  1. The user initiates a request by providing text and optional parameters like voice ID, speed, or format.
  2. The skill validates the presence of the SILICONFLOW_API_KEY via environment variables or the local config.
  3. A request is sent to the SiliconFlow API endpoint (api.siliconflow.cn) utilizing the CosyVoice2 model.
  4. The resulting audio data is streamed back to the local machine.
  5. The skill automatically saves the audio as a local file (e.g., MP3 or WAV) for immediate use.

SiliconFlow TTS Generation Setup

To get started with this skill, install it via the clawhub CLI and configure your API credentials:

# Install the skill
npx clawhub install siliconflow-tts-gen

# Set your SiliconFlow API key environment variable
export SILICONFLOW_API_KEY="your-api-key"

You can also store your key in ~/.openclaw/openclaw.json to allow Openclaw Skills to automatically detect your credentials.

SiliconFlow TTS Generation Data Schema & Taxonomy

The skill manages audio output and configuration through the following schema:

Data Component Location / Type Description
API Key Environment Variable SILICONFLOW_API_KEY used for authentication
Config File ~/.openclaw/openclaw.json Local storage for persistent API configurations
Audio Output Local File System Generated files saved in formats like mp3, opus, wav, or pcm
Script Source scripts/generate.py The core execution logic for the TTS synthesis

SiliconFlow TTS Generation Advanced Features

  • Rapid voice cloning capabilities requiring only a 3-second audio sample for custom voices.
  • Comprehensive support for Chinese dialects including Cantonese, Sichuan, Shanghai, Tianjin, and Wuhan.
  • High-precision speed control ranging from 0.25x to 4.0x to match specific timing requirements.
  • Ultra-low latency architecture designed for high-performance Openclaw Skills integrations.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*