feishu-voice-tts将文本通过 MOSS-TTS 转换为语音,并发送到飞书群/个人。支持语音消息格式(带波形条)。
Install via ClawdBot CLI:
clawdbot install helloeveryworlds/feishu-voice-ttsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://studio.mosi.cn/v1/audio/ttsUses known external API (expected, informational)
open.feishu.cnAudited Apr 16, 2026 · audit v1.0
Generated Mar 20, 2026
Used by HR or management to send voice announcements to company-wide or departmental Feishu groups, enhancing engagement and accessibility for employees, especially in remote or multilingual teams where text may be less effective.
Enables customer support teams to convert automated text responses into voice messages sent to Feishu groups or individual users, providing a more personalized and immediate service experience for inquiries or updates.
Allows educators or training platforms to send voice-based lessons or instructions to Feishu groups for students, facilitating auditory learning and accessibility for visual or reading-impaired learners in online courses.
Used by organizations to broadcast urgent voice alerts to Feishu groups, such as safety warnings or system outages, ensuring critical information is conveyed clearly and quickly to all members in real-time.
Offer the skill as a subscription service with tiered plans based on usage volume, such as number of voice messages sent per month, targeting businesses that require regular automated communication through Feishu.
License the underlying TTS and Feishu integration technology to other developers or companies for embedding into their own applications, generating revenue through one-time fees or usage-based royalties.
Provide consulting services to customize the skill for specific industry needs, such as integrating with existing CRM systems or developing specialized voice profiles, with revenue from project-based contracts.
💬 Integration Tip
Ensure ffmpeg is installed and MOSS_API_KEY is configured; verify Feishu app permissions are properly set in the developer console.
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.