feishu-audio将音频文件转换为飞书可播放的语音消息。先用 ffmpeg 转为 opus 格式，再上传到飞书，最后发送 audio 消息。适用于用户想要在飞书中收到可播放的语音消息的场景。
Install via ClawdBot CLI:
clawdbot install tianyn1990/feishu-audioGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated Mar 5, 2026
This skill enables businesses to send automated voice alerts, such as system status updates or reminders, directly to employees via Feishu. It is ideal for IT departments or operations teams needing to broadcast time-sensitive information in an accessible audio format, ensuring critical messages are heard promptly.
Support teams can use this skill to convert text-based responses into voice messages sent through Feishu, providing a more personal touch in customer interactions. It helps in scenarios where written communication is insufficient, such as explaining complex instructions or offering empathetic support, enhancing customer satisfaction.
Educators and trainers can leverage this skill to distribute audio lessons or announcements to students via Feishu, making learning materials more engaging. It supports remote education by allowing instructors to send voice explanations or feedback, catering to auditory learners and improving accessibility in educational settings.
Organizations can integrate this skill to send voice memos or briefings to team members on Feishu, streamlining internal communications. It is useful for managers sharing quick updates or for collaborative projects where verbal cues add clarity, fostering better team alignment and reducing miscommunication.
Offer this skill as part of a subscription-based service for businesses using Feishu, providing regular updates and premium support. Revenue is generated through monthly or annual fees, targeting companies that rely on automated communication tools to enhance productivity and internal messaging efficiency.
Provide a basic version of the skill for free with limited usage, while charging for advanced features like higher audio quality, bulk messaging, or analytics. This model attracts small teams initially and upsells to larger enterprises needing scalable solutions for voice communication within Feishu.
Generate revenue by offering custom integration and consulting services to tailor the skill for specific business needs, such as connecting with other TTS systems or enterprise workflows. This targets organizations with unique requirements, providing one-time project fees or ongoing maintenance contracts.
💬 Integration Tip
Ensure ffmpeg is installed and Feishu app credentials are correctly configured in environment variables to avoid common setup issues.
Scored Apr 19, 2026
Local speech-to-text with the Whisper CLI (no API key).
ElevenLabs text-to-speech with mac-style say UX.
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.
Local text-to-speech via sherpa-onnx (offline, no cloud)
Start voice calls via the OpenClaw voice-call plugin.