quick-ttsZero-config text-to-speech — give text, get an mp3 file. Handles natural-language voice selection ("用女声", "撒娇语气", "生气一点") and auto-inserts pacing breaks for...
Install via ClawdBot CLI:
clawdbot install scikkk/quick-ttsGrade Fair — 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.cnAI Analysis
The skill sends user-provided text to a documented third-party TTS API (SenseAudio) which is consistent with its stated purpose and requires explicit user API key configuration. No credential harvesting, hidden instructions, or obfuscation is present, but it does involve external data processing.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Creators can quickly generate voiceovers for videos or podcasts by providing text and natural voice requests like "用女声" or "撒娇语气", without needing technical API knowledge. The auto-pacing for long text ensures smooth audio for engaging posts, enhancing audience retention.
Educators can synthesize speech for online courses or language learning materials by specifying voices such as "儿童" or "温柔御姐" to match different lessons. The zero-config setup allows easy integration into platforms for generating audio explanations or reading assignments.
Businesses can use this skill to generate automated voice responses for IVR systems or chatbots, with voice selection like "生气一点" for urgency or "男声" for neutrality. It handles long texts with pacing breaks, improving call flow and user experience.
Developers can integrate this skill into applications to provide text-to-speech for visually impaired users, supporting natural voice requests like "沙哑" or "乐观" for personalized audio. The simple API call and error handling ensure reliable audio output for reading content aloud.
Offer this skill as part of a subscription plan where users pay monthly for a certain number of audio generations, leveraging the natural-language voice mapping to attract non-technical customers. Revenue comes from tiered pricing based on usage characters and voice options.
License the skill to e-learning or social media platforms as an embedded feature, charging a flat fee or per-transaction royalty. The zero-config nature reduces integration costs, making it appealing for platforms seeking quick TTS capabilities without development overhead.
Provide basic voice synthesis for free with limited characters, then upsell premium voices like "病娇" or "妩媚" and advanced features such as higher pacing control. Revenue is generated from upgrades and additional API key purchases for heavy users.
💬 Integration Tip
Ensure the SENSEAUDIO_API_KEY is securely stored as an environment variable, and use the provided bash script with curl and jq for reliable API calls and error handling.
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.