百度语音识别 - 将语音消息转换为文本。支持中文普通话、英语、粤语、四川话。专为国内服务器环境优化，自动绕过代理访问百度 API。
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
本 skill 用于将用户发送的语音消息（ogg/opus 格式）转换为文本。使用百度语音识别 API，专为国内服务器 + 代理环境优化。
proxychains4 代理访问海外服务（Discord、WhatsApp 等）unset LD_PRELOAD 绕过 proxychains 注入| 脚本 | 路径 | 用途 |
|---|---|---|
ogg_to_text.sh | /root/.openclaw/workspace/scripts/ogg_to_text.sh | 推荐 - 简单易用 |
speech_to_text.sh | /root/.openclaw/workspace/scripts/speech_to_text.sh | 完整功能版 |
baidu_speech_to_text.py | /root/.openclaw/workspace/scripts/baidu_speech_to_text.py | Python 主脚本 |
/root/.openclaw/workspace/scripts/ogg_to_text.sh <音频文件路径>
# 转换用户语音消息
/root/.openclaw/workspace/scripts/ogg_to_text.sh /root/.openclaw/media/inbound/xxxxx.ogg
| 参数 | 语言 |
|---|---|
--lang zh | 中文普通话（默认） |
--lang en | 英语 |
--lang cantonese | 粤语 |
--lang sichuan | 四川话 |
/root/.openclaw/workspace/scripts/speech_to_text.sh <音频文件> --pro
用户通过 WhatsApp/Discord 发送的语音消息保存在：
/root/.openclaw/media/inbound/
文件格式通常为 .ogg（Opus 编码），脚本会自动转换为 PCM 格式。
当用户发送语音消息并请求转文本时：
/root/.openclaw/media/inbound/*.ogg）/root/.openclaw/workspace/scripts/ogg_to_text.sh /root/.openclaw/media/inbound/<文件名>.ogg
| 阶段 | 耗时 | 说明 |
|---|---|---|
| 获取 token | ~100ms | 可缓存优化 |
| ogg 转 pcm | ~150-220ms | ffmpeg 转换 |
| API 调用 | ~400-600ms | 主要耗时 |
| 总计 | ~700-1000ms |
使用环境变量提供百度 API 账号信息（请勿写入仓库）：
export BAIDU_APP_ID="your_app_id"
export BAIDU_API_KEY="your_api_key"
export BAIDU_SECRET_KEY="your_secret_key"
端点：
| 错误 | 原因 | 解决方案 |
|---|---|---|
| SSL 错误 | 代理影响 | 确保使用 wrapper 脚本（.sh），不要直接调用 Python |
| 识别结果为空 | 静音或无语音 | 告知用户音频可能没有语音内容 |
| 3301 错误 | 音频质量差 | 请用户重新录制 |
| 3303 错误 | 语音过长 | 需要分段处理 |
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
The English summary is being prepared. Showing the original description.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
The English summary is being prepared. Showing the original description.
Use when you have a written implementation plan to execute in a separate session with review checkpoints
The English summary is being prepared. Showing the original description.
帮助用户将飞书群机器人 Webhook 通知接入 Claude Code，使得每次任务完成后自动发送飞书消息卡片通知。 触发场景（当用户提到以下任意内容时激活此 skill）： - "飞书通知"、"接入飞书"、"飞书提醒" - "task 完成通知"、"任务完成提醒" - "claude 完成提醒"、"claude 通知" - "Stop hook 通知"、"hook 通知" - "发飞书消息"、"飞书机器人" - "任务结束通知"、"配置通知"
The English summary is being prepared. Showing the original description.
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
The English summary is being prepared. Showing the original description.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
The English summary is being prepared. Showing the original description.