← Back to Skills Marketplace
scikkk

Pronunciation Coach

by scikkk · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
233
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install pronunciation
Description
Foreign language pronunciation coach — listen to standard TTS pronunciation, record yourself, get word-by-word feedback on what was wrong, then practice targ...
Usage Guidance
This skill appears to do what it says: generate TTS, send user audio to SenseAudio for ASR, compare transcripts, and save session data locally. Before installing or using it, consider: (1) audio and transcripts will be sent to a third-party endpoint (https://senseaudio.cn) — review their privacy policy and confirm you are comfortable with that; (2) keep your SENSEAUDIO_API_KEY secret (it grants access/billing to that service); (3) the skill will write files (audio, JSON) to the current directory — move or delete these if they contain sensitive content; (4) ensure curl/jq/xxd are available and from trusted system packages; and (5) if you need on-device-only processing or stricter privacy, do not use this cloud-based skill. If you want stronger assurance, ask the publisher for documentation of data retention and security practices for SenseAudio's API.
Capability Analysis
Type: OpenClaw Skill Name: pronunciation Version: 1.0.0 The skill functions as a legitimate pronunciation coach using the SenseAudio API (api.senseaudio.cn). It uses standard system utilities (curl, jq, xxd) to perform text-to-speech and speech-to-text operations, and it maintains a local progress file (pronunciation_progress.json). No evidence of malicious intent, data exfiltration, or unauthorized command execution was found.
Capability Assessment
Purpose & Capability
The name/description (pronunciation coach) matches the declared dependency on SENSEAUDIO_API_KEY and the runtime cURL commands to SenseAudio TTS/ASR endpoints. Required binaries (curl, jq, xxd) are directly used in the provided shell examples and are proportionate to the task.
Instruction Scope
SKILL.md instructs the agent to upload user audio to SenseAudio, transcribe results, produce and save TTS audio files, and write a local progress file. This is within scope, but it means user voice data and transcripts are sent to a third-party service and session data are stored locally; users should be aware of the privacy implications.
Install Mechanism
No install steps or external downloads are specified (instruction-only). That minimizes installation risk; the skill relies only on standard CLI tools present on the host.
Credentials
Only one environment variable is required: SENSEAUDIO_API_KEY, which is the expected credential for calling SenseAudio APIs. No unrelated credentials or extra secrets are requested.
Persistence & Privilege
The skill writes audio and JSON files (standard_slow.mp3, standard_normal.mp3, asr_result.json, pronunciation_progress.json) in the current directory to track sessions. It does not request elevated privileges or always-enable behavior, but users should note local storage of potentially sensitive data.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install pronunciation
  3. After installation, invoke the skill by name or use /pronunciation
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
senseaudio-pronunciation-coach v1.0.0 - Initial release of the pronunciation coaching tool for foreign language learners - Allows users to listen to standard TTS, record themselves, and receive word-by-word feedback - Offers practice material via direct input, preset scenes, or targeted phoneme drills - Analyzes recordings to diagnose specific phoneme issues, with tailored drills and accuracy tracking - Tracks progress and provides visual summaries of pronunciation weaknesses over multiple sessions
Metadata
Slug pronunciation
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Pronunciation Coach?

Foreign language pronunciation coach — listen to standard TTS pronunciation, record yourself, get word-by-word feedback on what was wrong, then practice targ... It is an AI Agent Skill for Claude Code / OpenClaw, with 233 downloads so far.

How do I install Pronunciation Coach?

Run "/install pronunciation" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Pronunciation Coach free?

Yes, Pronunciation Coach is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Pronunciation Coach support?

Pronunciation Coach is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Pronunciation Coach?

It is built and maintained by scikkk (@scikkk); the current version is v1.0.0.

💬 Comments