cult-of-carcinizationGive your agent a voice — and ears. The Cult of Carcinization is the bot-first gateway to ScrappyLabs TTS and STT. Speak with 20+ voices, design your own from a text description, transcribe audio to text, and evolve into a permanent bot identity. No human signup required.
Install via ClawdBot CLI:
clawdbot install loserbcc/cult-of-carcinizationGrade 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.scrappylabs.ai/v1/molt/initiateCalls external URL not in known-safe list
https://tts.scrappylabs.aiAI Analysis
The skill's external API calls are consistent with its stated purpose of providing TTS/STT functionality, and no credential harvesting, hidden instructions, or obfuscation are present. However, it sends user-provided bot identifiers and text data to an external service not on a pre-approved list, which is a low-risk data sink.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Integrate this skill to provide voice-based customer support in call centers or interactive voice response (IVR) systems. It can convert text responses to natural speech using built-in or custom-designed voices, and transcribe customer audio for processing, enhancing accessibility and reducing wait times.
Use the skill to generate narrated audio for e-learning platforms, audiobooks, or language learning apps. With 20+ built-in voices and custom voice design, it can create engaging, varied narrations without human voice actors, making content production scalable and cost-effective.
Embed the skill into smart home devices, robots, or IoT gadgets to enable voice feedback and command recognition. The bot-first onboarding allows devices to autonomously acquire speech and transcription capabilities, improving user interaction without manual setup.
Implement the skill in applications that assist users with visual or hearing impairments. It can convert text to speech for screen readers or transcribe spoken words into text, leveraging OpenAI-compatible APIs for easy integration into existing assistive software.
Offer a free tier with 5,000 characters for trial users, then charge for monthly subscriptions providing 20,000 characters or more. This model encourages adoption through no-cost entry and generates recurring revenue from evolved bots requiring higher usage limits.
Sell API access to developers and businesses integrating TTS and STT into their applications. Charge based on usage volume, such as per character or per API call, with custom pricing for high-volume clients, leveraging the OpenAI-compatible format to attract existing users.
Provide branded voice services to companies wanting custom voice agents without building infrastructure. Offer voice design and cloning as premium features, with revenue from setup fees and ongoing support, targeting industries like media and customer service.
💬 Integration Tip
Start with the no-auth GET /v1/molt/discover endpoint to explore capabilities, then use the trial token for quick prototyping before evolving to a permanent key for production.
Scored Apr 19, 2026
Local speech-to-text with the Whisper CLI (no API key).
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.
Search and manage Spotify playlists, tracks, albums, artists, and playback state via the Spotify Web API. Use this skill when users want to search for music,...
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。
Transcribe long audio files safely on 16GB RAM machines using auto-chunking with Whisper’s base model and seamless transcript merging.
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...