feishu-voice-lobster实现飞书语音消息的上传下载、语音转文字及文字转语音,支持与 ElevenLabs 语音服务集成。
Install via ClawdBot CLI:
clawdbot install godzff/feishu-voice-lobsterGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://api.elevenlabs.io/v1/speech-to-text?enable_logging=trueUses known external API (expected, informational)
open.feishu.cnAudited Apr 16, 2026 · audit v1.0
Generated Mar 21, 2026
Businesses integrate this skill into their Feishu-based customer support systems to handle voice inquiries. It automatically transcribes customer voice messages, generates responses using AI, and sends back voice replies, reducing manual workload and improving response times.
Educational platforms use this skill to create interactive voice-based language practice tools. Learners send voice messages in a target language, receive transcriptions for feedback, and get spoken responses to enhance pronunciation and conversational skills.
Companies deploy this skill within Feishu for internal communication, allowing employees to send voice updates or reports. It transcribes messages for documentation and can generate voice summaries, facilitating efficient information sharing in multilingual teams.
Organizations implement this skill to make Feishu more accessible for users with visual or motor impairments. It converts voice inputs to text for processing and outputs voice responses, enabling hands-free communication and navigation within the platform.
E-commerce platforms integrate this skill into Feishu to allow customers to place orders or inquire about products via voice. It processes voice commands, confirms details through text-to-speech, and streamlines the shopping experience without typing.
Offer this skill as a subscription service on a platform like Feishu Marketplace, charging businesses monthly or annually based on usage tiers. Revenue comes from recurring fees for access to voice processing and integration features.
Monetize by charging per API call for voice-to-text and text-to-speech conversions, with businesses paying based on the volume of messages processed. This model suits companies with fluctuating voice interaction needs.
License the skill technology to other companies for embedding into their own Feishu apps or services, with upfront licensing fees and ongoing support contracts. This targets developers and enterprises seeking custom voice solutions.
💬 Integration Tip
Ensure proper Feishu app permissions and FFmpeg installation for smooth audio conversion, and test with real voice samples to optimize ElevenLabs API usage.
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.