smallest-aiUltra-fast text-to-speech and speech-to-text via Smallest AI's Lightning v3.1 and Pulse models. Use when the user wants to generate speech, convert text to v...
Install via ClawdBot CLI:
clawdbot install abhishekmishragithub/smallest-aiGrade 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.smallest.ai/waves/v1/lightning-v3.1/get_speechCalls external URL not in known-safe list
https://waves.smallest.aiAI Analysis
The skill sends user-provided text to a documented, legitimate third-party API (Smallest AI) for text-to-speech processing, which is consistent with its stated purpose. While this involves external data transmission, it requires explicit user configuration of an API key and appears to be a standard integration without hidden instructions or credential harvesting patterns.
Audited Apr 16, 2026 · audit v1.0
Generated Mar 21, 2026
Deploy ultra-low latency TTS for interactive voice response systems in call centers, enabling sub-100ms speech generation to reduce wait times and improve customer experience. Use multilingual support like Hindi or Spanish for global customer bases, with voice selection rules adapting to language preferences.
Generate speech for educational videos and audiobooks in over 30 languages, leveraging code-switching for bilingual lessons. Use STT with diarization to transcribe student audio submissions, enabling automated feedback and accessibility features for diverse learners.
Integrate fast STT (64ms TTFT) for transcribing user voice memos into text, with emotion detection for sentiment analysis. Use TTS to read back notes aloud with configurable voices, ideal for productivity tools targeting professionals and students.
Produce dubbed audio for videos and podcasts using voice cloning and multilingual TTS, with specific voices like advika for Hindi or camilla for Spanish. Utilize STT timestamps for accurate subtitle synchronization, streamlining content adaptation for international audiences.
Implement TTS to read medical instructions aloud in multiple languages, enhancing accessibility for non-native speakers. Use STT with diarization to transcribe doctor-patient conversations for automated note-taking, improving record-keeping efficiency in clinics.
Offer a free tier with 30 minutes/month of TTS to attract users, then upsell to paid plans like Basic at $5/month for 3 hours of TTS and voice cloning. Generate revenue through tiered subscriptions based on usage limits and advanced features like emotion detection.
Provide custom enterprise plans with higher limits and dedicated support for industries like customer service or media, charging based on API call volume or minutes processed. Include premium features such as custom voice training and priority access to reduce latency further.
Partner with e-learning platforms, productivity apps, or call center software to embed TTS and STT capabilities, earning revenue through revenue-sharing or per-user licensing. Leverage the skill's multilingual support to enhance partner offerings in global markets.
💬 Integration Tip
Ensure the SMALLEST_API_KEY is set in the environment and use the provided shell scripts for quick integration with minimal dependencies like curl.
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...