OpenClaw

pronunciation-coach

Pronunciation coaching with real voice analysis using Azure Speech Services. Analyzes audio files for phoneme-level accuracy, fluency, prosody, and intonation scores.

crazybuffon0 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install crazybuffon/pronunciation-coach

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

Pronunciation Coach

Analyze spoken English pronunciation using Azure Speech Services and provide actionable coaching feedback.

Privacy Note: This skill reads local voice messages from ~/.openclaw/media/inbound/ and transmits them to Microsoft Azure Speech Services for processing.

Prerequisites

Azure Speech API Key: Set AZURE_SPEECH_KEY env var
Azure Speech Region: Set AZURE_SPEECH_REGION env var (e.g., southeastasia)
ffmpeg: Required for audio format conversion (must be on PATH)
Node.js: Required for report generation

Workflow

1. Receive Audio

Voice messages from Telegram are stored in ~/.openclaw/media/inbound/. Find the latest .ogg file matching the message timestamp.

ls -lt ~/.openclaw/media/inbound/*.ogg | head -5

2. Run Assessment

scripts/pronunciation-assess.sh <audio_file> "<reference_text>"

audio_file: Path to the voice message (ogg/wav/mp3/m4a)
reference_text: What the speaker intended to say (from transcript)
The script auto-converts any format to WAV 16kHz mono

3. Generate Report

Pipe the JSON output into the report generator:

scripts/pronunciation-assess.sh audio.ogg "reference text" | node scripts/pronunciation-report.js

The report includes:

Overall scores (Pronunciation, Accuracy, Fluency, Prosody, Completeness)
Word-by-word breakdown with per-phoneme scores
Problem sounds highlighted
Verdict with actionable next steps

4. Provide Coaching

After generating the report:

Send the text report to the user (scores + word breakdown)
Identify top 3 problem sounds from the phoneme scores
Explain each problem — what the correct sound is and how to produce it
- See references/phoneme-guide.md for phoneme descriptions and fixes
Send a voice message (via TTS) demonstrating the correct pronunciation of problem words
Assign practice — give the user specific sentences to re-record focusing on wea...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/crazybuffon/pronunciation-coach
Version: —
Commit: e7a63c207ae6baa0b743d0710f7808f9a858e012
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# Pronunciation Coach

Analyze spoken English pronunciation using Azure Speech Services and provide actionable coaching feedback.

**Privacy Note**: This skill reads local voice messages from `~/.openclaw/media/inbound/` and transmits them to Microsoft Azure Speech Services for processing.

## Prerequisites

- **Azure Speech API Key**: Set `AZURE_SPEECH_KEY` env var
- **Azure Speech Region**: Set `AZURE_SPEECH_REGION` env var (e.g., `southeastasia`)
- **ffmpeg**: Required for audio format conversion (must be on PATH)
- **Node.js**: Required for report generation

## Workflow

### 1. Receive Audio

Voice messages from Telegram are stored in `~/.openclaw/media/inbound/`. Find the latest `.ogg` file matching the message timestamp.

```bash
ls -lt ~/.openclaw/media/inbound/*.ogg | head -5
```

### 2. Run Assessment

```bash
scripts/pronunciation-assess.sh <audio_file> "<reference_text>"
```

- `audio_file`: Path to the voice message (ogg/wav/mp3/m4a)
- `reference_text`: What the speaker intended to say (from transcript)
- The script auto-converts any format to WAV 16kHz mono

### 3. Generate Report

Pipe the JSON output into the report generator:

```bash
scripts/pronunciation-assess.sh audio.ogg "reference text" | node scripts/pronunciation-report.js
```

The report includes:
- Overall scores (Pronunciation, Accuracy, Fluency, Prosody, Completeness)
- Word-by-word breakdown with per-phoneme scores
- Problem sounds highlighted
- Verdict with actionable next steps

### 4. Provide Coaching