voice-translator说中文出外语语音——按住说中文，2-3秒内播放英/日/韩语音。支持场景模式、双向对话、常用句收藏。
Install via ClawdBot CLI:
clawdbot install scikkk/voice-translatorGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://api.senseaudio.cn/v1/t2a_v2Calls external URL not in known-safe list
https://senseaudio.cn/docsAI Analysis
The skill's external API calls (api.senseaudio.cn) are directly related to its stated purpose of voice translation (ASR, translation, TTS) and are documented in the skill definition. There is no evidence of credential harvesting, hidden instructions, or obfuscation. The primary risk is sending user audio data to a third-party service not on a pre-approved list, which is a standard dependency risk for cloud-based AI features.
Audited Apr 18, 2026 · audit v1.0
Generated Mar 22, 2026
Travelers can use the skill to communicate in foreign countries for common situations like ordering food, asking for directions, or checking into hotels. It provides real-time voice translation with context-aware phrases, reducing language barriers during trips.
Professionals in multinational settings can facilitate conversations by translating spoken phrases between languages during informal discussions or negotiations. It supports bidirectional mode for seamless dialogue between parties.
Patients or medical staff can use the skill to translate symptoms, requests, or instructions in medical settings, ensuring clear communication during emergencies or consultations abroad.
Shop assistants or customers can translate inquiries about products, prices, or payments in shopping scenarios, enhancing customer experience in international retail environments.
Language learners can practice pronunciation and comprehension by speaking phrases and hearing translations, using the skill as an interactive aid for real-world conversation practice.
Offer tiered subscription plans for developers or businesses to access the ASR, translation, and TTS APIs. Revenue comes from monthly fees based on usage limits, such as number of translations or audio minutes.
License the skill as a white-label solution for travel apps, communication platforms, or IoT devices. Charge upfront licensing fees or per-user royalties for integration into third-party products.
Develop a standalone mobile app with free basic translations and premium features like offline mode, advanced scene modes, or ad-free experience. Monetize through in-app purchases and advertisements.
💬 Integration Tip
Ensure the SENSEAUDIO_API_KEY is securely stored and consider caching translations to reduce API calls and latency.
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.