A comprehensive Text-to-Speech and voice feature extraction skill for Gitee AI, supporting over 15 state-of-the-art voice models.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install moark-tts
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install moark-tts 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 Moark-TTS Gitee AI Suite?
Moark-TTS is a robust speech synthesis engine designed for the Openclaw Skills ecosystem, providing a unified interface for Gitee AI voice services. It enables developers to integrate advanced Text-to-Speech (TTS) capabilities and voice feature extraction into their AI agents with minimal configuration.
The skill supports a massive library of industry-leading models including CosyVoice, ChatTTS, and Qwen-TTS. By abstracting model-specific complexities, Moark-TTS allows for seamless voice cloning, emotion control, and multi-speaker synthesis through a standardized CLI workflow.
Moark-TTS Gitee AI Suite Use Cases
- Generating natural-sounding narrations for content creators using models like AudioFly or CosyVoice.
- Performing high-fidelity voice cloning preparation through CosyVoice-300M voice feature extraction.
- Building multilingual AI assistants with localized speech using Qwen3-TTS and Step-Audio-TTS.
- Creating expressive audio with fine-tuned emotion mixing and pitch control for gaming or storytelling.
- Batch processing text-to-audio synthesis using efficient async workflows for enterprise SaaS.
How Moark-TTS Gitee AI Suite Works
- The user selects a specific TTS model or voice extraction task from the 15 supported options.
- The skill validates the presence of the GITEEAI_API_KEY environment variable to ensure authorized access.
- Model-specific parameters (such as emotion alpha, prompt audio URLs, or speaker IDs) are gathered based on the chosen engine.
- The
perform_tts.pyorperform_voice_feature_extraction.pyscript is executed via the Python runtime. - The skill communicates with Gitee AI endpoints, supporting both synchronous and asynchronous processing modes.
- Output is parsed and returned as a direct audio URL, local file path, or serialized voice feature result.
Moark-TTS Gitee AI Suite Setup
Ensure you have Python installed and your Gitee AI credentials ready. This skill is built with standard libraries and does not require complex dependency managers.
# Set your API Key
export GITEEAI_API_KEY="your_api_key_here"
# Run a basic TTS synthesis
python scripts/perform_tts.py --model cosyvoice2 --text "Hello, welcome to Openclaw Skills." --voice alloy
# Run voice feature extraction
python scripts/perform_voice_feature_extraction.py --model FunAudioLLM-CosyVoice-300M --prompt "Style guide" --file-url "https://example.com/sample.mp3"
Moark-TTS Gitee AI Suite Data Schema & Taxonomy
Moark-TTS utilizes a structured parameter mapping system to translate OpenAI-compatible SDK calls into model-specific requests. Data is organized as follows:
| Data Type | Description |
|---|---|
| Model ID | One of 15 identifiers (e.g., qwen-tts, audiofly, glm-tts). |
| Input JSON | Structured array for multi-item inputs in Qwen3-TTS. |
| Reference Audio | URL-based audio prompts for style-conditioning and cloning. |
| Metadata | Includes X-Failover-Enabled headers and async gender/pitch hints. |
| Output | Returns AUDIO_URL, AUDIO_FILE, or VOICE_URL based on the response format. |
Moark-TTS Gitee AI Suite Advanced Features
- Multi-Speaker Synthesis: Utilize
--qwen-inputs-jsonto combine built-in and custom voices in a single request. - Emotion Control: Fine-tune output using
emo_alphaandemo_textfor nuanced IndexTTS-2 generations. - Failover Protection: Built-in high-availability support with default
X-Failover-Enabledlogic. - Custom Style Injection: Support for
prompt_wav_urlandinstruct_textfor advanced speaking style guidance. - Flexible API Mapping: Automatic mapping of
extra_bodyJSON fields to internal CLI flags for OpenAI SDK compatibility.
SKILL.md
Loading
Related Openclaw Skills
Nano Banana 2
A professional-grade image generation and editing tool powered by Google's Gemini 3.1 Flash Image model for creating high-fidelity visual assets.
Claw Security Panel
A professional security auditing dashboard for OpenClaw environments that detects vulnerabilities and provides automated remediation.
Weather API Tool
A professional-grade AI skill that enables autonomous agents to fetch, parse, and utilize structured weather data from global providers.
Market Analysis Service
A comprehensive market intelligence tool providing automated enterprise trend analysis, competitor tracking, and deep user behavior insights.
Deterministic Calc
A precision-focused skill that replaces AI numerical guesswork with reliable code-based execution for mathematical and shell operations.
Novel Writer Skill
An automated creative writing agent designed to draft high-quality long-form novels while maintaining strict narrative consistency and period-accurate details.
Featured*
