feishu-voice-reply-huoshan通过火山引擎 TTS 合成多音色语音,转换为 Opus 格式后,使用飞书 API 自动上传并发送语音消息。
Install via ClawdBot CLI:
clawdbot install kaqzsd/feishu-voice-reply-huoshanGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://openspeech.bytedance.com/api/v3/tts/unidirectionalCalls external URL not in known-safe list
https://www.volcengine.com/Uses known external API (expected, informational)
open.feishu.cnAI Analysis
The skill's external API calls (Volcano Engine TTS, Feishu) are consistent with its stated purpose of generating and sending voice messages. While it sends user-provided text to a third-party TTS service, this is a necessary function and the endpoint is documented. No evidence of credential harvesting, hidden instructions, or obfuscation was found.
Generated Mar 21, 2026
Enables automated voice responses in customer service chats on Feishu, using TTS to convert text replies into natural-sounding speech for quick issue resolution. Ideal for handling common inquiries without manual agent intervention, improving response times and user experience.
Sends voice alerts for urgent updates or reminders within company teams on Feishu, such as meeting reminders or system outages. Enhances communication clarity and ensures critical information is conveyed effectively through auditory cues.
Facilitates voice-based learning materials by converting text lessons into speech for students on Feishu platforms. Supports multiple voice styles to make educational content more engaging and accessible, especially for auditory learners.
Creates personalized voice messages for marketing promotions sent via Feishu to target audiences. Uses varied TTS voices to add a human touch to automated campaigns, increasing engagement and conversion rates through auditory appeal.
Provides voice output for visually impaired users in Feishu communications, converting text messages into speech to enhance accessibility. Ensures inclusive communication by offering alternative formats for information consumption.
Offers the skill as a paid subscription service on platforms like Feishu marketplace, with tiered pricing based on usage limits or advanced voice features. Generates recurring revenue from businesses needing automated voice messaging solutions.
Monetizes through a usage-based model where customers pay per voice message generated or per API call to the TTS and Feishu integration. Attracts small to medium businesses with flexible pricing and low entry costs.
Sells custom licenses to large enterprises for on-premise deployment or enhanced support, including integration with existing CRM or communication systems. Provides high-value contracts with dedicated technical assistance and customization options.
💬 Integration Tip
Ensure all environment variables are correctly set and test with a small message first to verify API connectivity and audio quality.
Scored Apr 19, 2026
Audited Apr 17, 2026 · audit v1.0
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.
Start voice calls via the OpenClaw voice-call plugin.
Local text-to-speech via sherpa-onnx (offline, no cloud)