feishu-voice-elevenlabsSend and receive voice messages on Feishu (Lark) using ElevenLabs TTS and STT. Activate when user asks to send a voice message on Feishu, or when receiving a...
Install via ClawdBot CLI:
clawdbot install dongdongbear/feishu-voice-elevenlabsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://elevenlabs.io/voice-libraryUses known external API (expected, informational)
open.feishu.cnAudited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Companies use this skill to automate voice-based customer inquiries on Feishu, transcribing user voice messages and responding with synthesized voice replies. This reduces response times and supports multilingual customers efficiently.
Organizations integrate the skill into Feishu for hands-free communication, allowing employees to send and receive voice messages during meetings or while multitasking. It enhances accessibility and streamlines workflow in fast-paced environments.
Educational platforms leverage the skill to provide voice interaction for language practice on Feishu, enabling students to send voice messages and receive feedback via TTS. It supports pronunciation correction and conversational practice.
Healthcare providers use the skill to offer voice-based appointment reminders and health tips on Feishu, transcribing patient queries and responding with clear voice instructions. This improves patient compliance and accessibility for elderly users.
Sales teams employ the skill to send personalized voice messages to leads on Feishu, using TTS for follow-ups and STT to transcribe responses. It adds a personal touch and increases engagement rates in campaigns.
Offer the skill as a subscription service on platforms like Feishu, charging businesses monthly fees based on usage tiers for voice message processing. Revenue comes from recurring payments and premium features like advanced voice customization.
License the underlying TTS and STT technology to other developers or enterprises for integration into their own Feishu apps. Revenue is generated through one-time licensing fees or usage-based pricing models.
Provide consulting services to businesses for customizing and deploying the skill within their Feishu workflows, including setup, training, and ongoing support. Revenue comes from project-based fees and maintenance contracts.
💬 Integration Tip
Ensure all environment variables are set correctly and test with sample audio files before full deployment to avoid API errors.
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.