A specialized skill for converting text to speech and sending it as native, playable audio messages in Feishu chats.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install feishu-audio-msg
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install feishu-audio-msg using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Feishu Audio?
The feishu-audio skill bridges the gap between AI text generation and interactive voice messaging within the Feishu ecosystem. While standard messaging tools often send audio as generic file attachments, this skill ensures that audio is delivered as a native voice message (msg_type=audio). This allows recipients to play the audio directly within the chat interface, providing a much more integrated and professional user experience when utilizing Openclaw Skills.
By automating the specific and often complex two-step API flow required by Feishu—uploading with a specific opus type and then sending as an audio message—this skill enables developers and AI agents to execute voice roll calls, speech announcements, and personalized voice notifications with minimal configuration.
Feishu Audio Use Cases
- Sending automated voice roll calls (语音报数) to operations or management groups.
- Providing accessibility features by converting AI-generated text responses into speech.
- Delivering real-time speech announcements for system alerts or project milestones.
- Facilitating voice-based task reminders or notifications directly to a user's direct message (DM).
How Feishu Audio Works
- The skill accepts a text string and a target recipient ID (chat_id or open_id) as input.
- It triggers a Text-to-Speech (TTS) engine using a specified or default voice profile like zh-CN-XiaoyiNeural.
- The skill executes a POST request to the Feishu /files endpoint, specifically flagging the file_type as opus to meet Feishu's internal requirements.
- Upon receiving a file_key, the skill sends a final POST request to the Feishu /messages endpoint using the audio message type for native playback.
Feishu Audio Setup
The feishu-audio skill is designed for zero-manual-setup in standard deployments by automatically reading credentials from your existing OpenClaw configuration. To use it via CLI or within an agent workflow, follow this structure:
bash /root/.openclaw/skills/feishu-audio/scripts/send_audio.sh \
"Your message content" \
"<chat_id or user open_id>" \
[optional_voice_id]
Ensure your credentials are correctly set in /root/.openclaw/openclaw.json under the channels.feishu.accounts.main path.
Feishu Audio Data Schema & Taxonomy
The skill manages the interface between text inputs and Feishu's binary requirements. The data organization is detailed below:
| Parameter | Value/Type | Description |
|---|---|---|
| receive_id_type | chat_id | Used for both groups (oc_xxx) and DMs (ou_xxx) |
| file_type | opus | Mandatory type for Feishu playable audio uploads |
| msg_type | audio | Ensures the message appears as a voice bubble |
| Voice Options | zh-CN / en-US | Supports multiple neural voices for natural output |
Feishu Audio Advanced Features
- Support for multiple high-quality neural voices including zh-CN-XiaoyiNeural, zh-CN-YunxiNeural, en-US-AriaNeural, and en-US-GuyNeural.
- Intelligent credential resolution that inherits authentication from the primary Openclaw Skills environment.
- Specialized API handling to bypass the 234001 upload error code common in custom Feishu integrations.
- Flexible routing that supports both group chat IDs (oc_xxx) and individual open IDs (ou_xxx).
SKILL.md
Loading
Related Openclaw Skills
Zocdoc Healthcare Finder & Booking
An AI agent skill that enables real-time search and booking for in-network doctors using the Zocdoc infrastructure.
ClawdBites: Instagram Recipe Extractor
A sophisticated extraction engine that converts Instagram reels into structured recipes using caption parsing, local audio transcription, and vision analysis.
Security Analysis
A professional security auditing tool designed to identify vulnerabilities, instruction injections, and data exfiltration risks within codebases and agent configurations.
Security Shield: SAST & Privacy Auditor
An automated security and privacy auditing skill that performs deep SAST analysis to identify vulnerabilities and PII leaks in codebases.
MiniMax Hailuo Video
A professional-grade skill for generating, monitoring, and downloading AI videos using the MiniMax S2V-01 model with character reference support.
Creative Agent OS North Star
An architectural governance skill ensuring AI agent development remains lightweight, cloud-compatible, and user-centric.
Featured*
