← Back to Skills Marketplace
250
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install quick-tts
Description
Zero-config text-to-speech — give text, get an mp3 file. Handles natural-language voice selection ("用女声", "撒娇语气", "生气一点") and auto-inserts pacing breaks for...
Usage Guidance
This skill will send the text you provide to SenseAudio's API (https://senseaudio.cn) using the SENSEAUDIO_API_KEY you supply, and will save an mp3 locally; do not send highly sensitive or private data to it. Ensure the API key you provide is limited in scope and can be revoked if needed. Verify that curl, jq, and xxd are available on the host and that the JSON response fields (.data, .extra_info, or base_resp) match the skill's assumptions before decoding — otherwise the jq/xxd pipeline could fail or produce garbage. Review SenseAudio's privacy/terms if you care about how submitted text is stored or logged by the provider.
Capability Analysis
Type: OpenClaw Skill
Name: quick-tts
Version: 1.0.0
The skill provides a text-to-speech interface using the SenseAudio API (api.senseaudio.cn). It maps natural language requests to specific voice IDs and processes the API response using standard tools like curl, jq, and xxd to generate MP3 files. No malicious intent, data exfiltration, or suspicious execution patterns were identified in SKILL.md.
Capability Assessment
Purpose & Capability
Name and description (quick TTS) align with the declared requirements: a single SENSEAUDIO_API_KEY and CLI tools (curl, jq, xxd) are exactly what's needed to call a remote TTS API and convert hex-encoded audio to an mp3.
Instruction Scope
Instructions stay within the TTS task (voice mapping, inserting pacing breaks, calling https://api.senseaudio.cn/v1/t2a_v2, decoding audio). Minor inconsistency: the document references checking base_resp.status_code/base_resp.status_msg but the curl/jq examples extract .data and .extra_info — the exact JSON field names should be validated before decoding to avoid errors. No instructions ask the agent to read unrelated files or other environment variables.
Install Mechanism
Instruction-only skill with no install spec or downloads — lowest-risk footprint (relies on existing curl/jq/xxd binaries).
Credentials
Only requests a single credential (SENSEAUDIO_API_KEY), which is appropriate for a remote TTS service. No unrelated secrets or config paths are requested.
Persistence & Privilege
Does not request always:true or any special persistent privileges. It is user-invocable and can be invoked autonomously (platform default), which is expected for skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install quick-tts - After installation, invoke the skill by name or use
/quick-tts - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of quick-tts skill for fast, zero-config text-to-speech conversion.
- Supports natural-language voice selection, including moods and specific voice types (e.g. "温柔御姐", "生气一点").
- Automatically inserts pacing breaks for longer texts to enhance natural speech rhythm.
- Simple API integration: just provide text, receive an mp3 file—no technical setup required.
- Error handling for common API responses, including invalid key, long text, and rate limiting.
Metadata
Frequently Asked Questions
What is Quick TTS?
Zero-config text-to-speech — give text, get an mp3 file. Handles natural-language voice selection ("用女声", "撒娇语气", "生气一点") and auto-inserts pacing breaks for... It is an AI Agent Skill for Claude Code / OpenClaw, with 250 downloads so far.
How do I install Quick TTS?
Run "/install quick-tts" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Quick TTS free?
Yes, Quick TTS is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Quick TTS support?
Quick TTS is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Quick TTS?
It is built and maintained by scikkk (@scikkk); the current version is v1.0.0.
More Skills