lark-voiceSend voice messages on Lark (Feishu) by converting text to speech. Use when the user asks to send a voice message or reply with voice.
Install via ClawdBot CLI:
clawdbot install cheerwhy/lark-voiceGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Generated May 9, 2026
A customer support agent on Lark uses the TTS skill to convert text-based answers into voice messages, providing a more personal touch. This is ideal for resolving queries quickly without typing long responses.
Managers convert important announcements into voice messages and send them to team chats on Lark. This ensures team members can listen while multitasking, improving information retention.
Educators send voice messages in a target language to students for pronunciation practice. The TTS skill converts lesson text into natural-sounding audio, aiding language acquisition.
Sales professionals send personalized voice messages to prospects after meetings, summarizing key points or next steps. This adds a human touch and increases engagement.
Charge users a monthly fee for access to premium TTS voices (e.g., expressive, multilingual) integrated into Lark. Revenue comes from recurring subscriptions for enhanced voice quality.
Offer a freemium model where basic TTS is free, but advanced features (e.g., longer messages, custom voice styles) are charged per voice message generated. Revenue scales with usage.
License the TTS skill to enterprises for internal use, allowing custom voice branding (e.g., company spokesperson voice). Revenue from one-time license fees and support contracts.
💬 Integration Tip
Ensure ffmpeg is installed on the system, and configure the TTS source as described in the skill's discovery logic to enable seamless voice message generation.
Scored May 9, 2026
Local speech-to-text with the Whisper CLI (no API key).
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
Search and manage Spotify playlists, tracks, albums, artists, and playback state via the Spotify Web API. Use this skill when users want to search for music,...
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Transcribe long audio files safely on 16GB RAM machines using auto-chunking with Whisper’s base model and seamless transcript merging.
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...