noizai-ttsUse this skill whenever the user wants to convert text into speech, generate audio from text, or produce voiceovers. Triggers include: any mention of 'TTS',...
Install via ClawdBot CLI:
clawdbot install Ksuriuri/noizai-ttsGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
upload → https://noiz.ai/v1/`Calls external URL not in known-safe list
https://example.com/my_voice.wavUses known external API (expected, informational)
discord.comAI Analysis
The skill sends user-provided text and potentially voice reference audio to an external API (Noiz.ai) and can download audio from arbitrary URLs, creating data exfiltration and supply chain risks. While the core functionality is documented, the permissions for network and filesystem access combined with external data processing warrant caution.
Generated Mar 20, 2026
Convert EPUB or PDF files into narrated audiobooks with chapter support and consistent voice mapping. Useful for publishers or authors creating audio versions of books, leveraging timeline mode for precise segment alignment and voice blending for character differentiation.
Generate time-aligned audio for video content by converting SRT subtitles into dubbed speech with voice cloning and emotion control. Ideal for localization teams or content creators needing multilingual voiceovers, using reference audio slicing to match original timestamps.
Transform articles or textbooks into audio lectures with per-segment voice control for different speakers or topics. Supports emotion modulation to enhance engagement, suitable for e-learning platforms creating accessible audio materials.
Produce short audio clips in formats like Opus or OGG for messaging apps or notifications, using simple mode with guest voices or custom cloning. Useful for developers integrating TTS into chatbots or communication tools without API keys.
Convert written content such as websites or documents into speech for visually impaired users, offering speed control and multiple language support. Enables organizations to provide audio alternatives quickly with fallback guest mode for low-cost deployment.
Offer cloud-based TTS services via the Noiz backend with premium features like emotion control and voice cloning. Charge monthly fees based on usage tiers, targeting businesses needing high-quality audio production without local infrastructure.
Provide a free version using guest mode with limited voices and features, while monetizing advanced capabilities like timeline rendering and Kokoro integration through one-time purchases or API key upgrades. Appeals to individual creators and small teams.
License the skill to third-party platforms such as Feishu, Telegram, or Discord for in-app audio generation, earning revenue through partnership agreements or per-transaction fees. Focus on expanding reach via existing user bases in communication and productivity tools.
💬 Integration Tip
Use environment variables for API keys to streamline deployment, and test guest mode first for proof-of-concept before committing to backend-specific features.
Scored Apr 19, 2026
Audited Apr 16, 2026 · audit v1.0
Transcribe audio files with speaker diarization (who speaks when). Supports 100+ languages, automatic language detection, and timestamps. Use for meetings, interviews, podcasts, or voice messages. Requires AssemblyAI API key.
使用 poocr 库识别发票并导出 Excel。当用户需要识别增值税发票、批量处理发票文件或提取发票信息到 Excel 时调用此技能。
Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...
Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.