← Back to Skills Marketplace
qwencloud-audio-tts
by
Cuixiaoyang123
· GitHub ↗
· v0.2.0
· MIT-0
131
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install qwencloud-audio-tts
Description
[QwenCloud] Synthesize speech from text with Qwen TTS models. TRIGGER when: user wants to convert text to speech, create voiceovers, generate audio narration...
Usage Guidance
What to consider before installing:
- The skill needs your Qwen/DashScope API key (DASHSCOPE_API_KEY or QWEN_API_KEY) to function, but the registry metadata incorrectly states 'none'. Do not paste your API key into chat — set it as an environment variable or in a local .env file and keep the key private.
- The bundled scripts read .env and search your repository for config/skill files and may write small files (audio outputs, response.json, and .agents/state.json). If you install this in a sensitive repo, review the code first or run it in an isolated environment.
- The code may run local subprocesses (used for update-checks) and can execute other local scripts if present; verify those scripts before allowing operations that run them.
- If you trust the source and want to use the skill: (1) inspect scripts/qwencloud_lib.py, scripts/tts.py and scripts/tts_cosyvoice.py to confirm they match your expectations; (2) provide the API key via environment or .env (not via chat); (3) consider running the scripts in a dedicated virtualenv or sandbox to avoid accidental exposure of repo secrets.
- If you do not trust the origin or cannot verify the code, do not install. At minimum request that the publisher update the registry metadata to list the required env vars and primary credential so it accurately reflects the skill's needs.
Capability Analysis
Type: OpenClaw Skill
Name: qwencloud-audio-tts
Version: 0.2.0
The skill provides legitimate text-to-speech functionality using QwenCloud APIs via HTTP and WebSocket. It includes a robust shared library (qwencloud_lib.py) for API interaction, environment management, and optional file uploads to Alibaba Cloud OSS. While it contains an update-check mechanism (gossamer.py) that uses subprocess calls and npx to manage skill installations, these behaviors are transparently documented in SKILL.md and designed to be executed only with user consent. The code follows security best practices by explicitly instructing the agent to mask API keys and avoid plaintext exposure.
Capability Tags
Capability Assessment
Purpose & Capability
The skill's stated purpose (Qwen TTS) matches the included scripts and documentation: tts.py and tts_cosyvoice.py implement HTTP and WebSocket TTS flows and expect a Qwen/DashScope API key. However, the registry metadata claims 'Required env vars: none' and 'Primary credential: none' while the SKILL.md and scripts clearly require DASHSCOPE_API_KEY or QWEN_API_KEY. This metadata omission is an incoherence that could mislead users about secret requirements.
Instruction Scope
SKILL.md and the scripts instruct the agent to load .env files, check environment variables, read bundled reference files, and (via agent-compatibility guidance) scan parent project files for other skills and optionally append entries to user config files (with user consent). The code also emits update-check signals and can invoke local scripts via subprocess. These file reads/writes and repository scans are within a TTS onboarding scope but broaden the agent's access to repository state and potentially secrets; the guidance to never print API keys mitigates risk but does not eliminate the fact that the skill loads and may access secrets.
Install Mechanism
This is an instruction-only skill with bundled Python scripts (no remote download/install spec). No external arbitrary archives or unknown URLs are fetched by an installer. Some scripts instruct the user to pip install dashscope for CosyVoice, which is normal; there is no packaged install that pulls code from an unknown host.
Credentials
The scripts legitimately require an API key (DASHSCOPE_API_KEY / QWEN_API_KEY) to access the TTS provider — that is proportional to the stated purpose. The problem is the registry metadata not declaring these required env vars or a primary credential. Additionally, load_dotenv injects .env into os.environ (it does not overwrite existing vars) and the skill reads environment variables and may write small state files under a repo .agents directory; users should be aware this will touch local repo state and could access secrets stored in .env.
Persistence & Privilege
always:false and agent-autonomy defaults are preserved (no forced always-on). The skill will write small local files (e.g., response.json, audio files under output/, and .agents/state.json via gossamer) and offers guidance to append entries to project config files (only after asking the user, per the doc). These repository writes are within the skill's scope but do persist data in the repo and may create or modify files under .agents or skills-related config.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install qwencloud-audio-tts - After installation, invoke the skill by name or use
/qwencloud-audio-tts - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.2.0
No user-facing or functional changes detected.
- Version bump to 0.2.0 with no file changes.
- No additions, removals, or edits in skill behavior or documentation.
v0.1.0
Initial release of qwencloud-audio-tts skill.
- Enables text-to-speech (TTS) synthesis using QwenCloud models for voice generation, narration, and TTS app building.
- Supports both Qwen TTS (HTTP API) and CosyVoice (WebSocket API) with separate scripts and clear model/voice selection guidance.
- Provides detailed setup, security, API key handling, and model compatibility instructions.
- Includes troubleshooting steps, sample execution commands, and documentation references for advanced usage.
- Ensures robust file output handling and post-execution diagnostics to guide users through common issues.
Metadata
Frequently Asked Questions
What is qwencloud-audio-tts?
[QwenCloud] Synthesize speech from text with Qwen TTS models. TRIGGER when: user wants to convert text to speech, create voiceovers, generate audio narration... It is an AI Agent Skill for Claude Code / OpenClaw, with 131 downloads so far.
How do I install qwencloud-audio-tts?
Run "/install qwencloud-audio-tts" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is qwencloud-audio-tts free?
Yes, qwencloud-audio-tts is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does qwencloud-audio-tts support?
qwencloud-audio-tts is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created qwencloud-audio-tts?
It is built and maintained by Cuixiaoyang123 (@cuixiaoyang123); the current version is v0.2.0.
More Skills