imessage-voice-memo-skillSend native iMessage voice bubbles with ElevenLabs TTS via BlueBubbles. Use when: user asks to send a voice message, wants something spoken aloud, storytelli...
Install via ClawdBot CLI:
clawdbot install amzzzzzzz/imessage-voice-memo-skillGrade 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.elevenlabs.io/v1/text-to-speech/{voice_id}Calls external URL not in known-safe list
https://github.com/amzzzzzzz/imessage-voice-memo-skillAI Analysis
The skill's external API calls (ElevenLabs TTS, BlueBubbles) are consistent with its stated purpose of sending voice messages via iMessage. While it sends user-provided text to an external service (ElevenLabs), this is a necessary function for the skill to operate and is documented. No credential harvesting, hidden instructions, or obfuscation were found.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 21, 2026
Users send expressive voice messages via iMessage for personal communication, such as sharing stories, jokes, or emotional updates with friends and family. This leverages ElevenLabs TTS for natural-sounding speech and BlueBubbles for native iOS integration, making conversations more engaging than text alone.
Businesses use this skill to send automated voice notifications or updates to customers via iMessage, such as order confirmations or appointment reminders. The native voice bubble format provides a more personal touch compared to standard text messages, potentially improving customer engagement and satisfaction.
Educators or content creators send voice summaries, storytelling sessions, or language lessons through iMessage to students or subscribers. This allows for auditory learning experiences with expressive TTS features, making educational material more accessible and engaging in a conversational format.
Teams within organizations use voice memos for quick updates, meeting summaries, or brainstorming sessions sent directly to colleagues via iMessage. This enhances remote collaboration by adding vocal nuance and reducing text-based misunderstandings, especially for complex or nuanced topics.
Offer a basic free tier with limited voice messages per month, then charge for higher usage, custom voices, or advanced TTS features via ElevenLabs integration. Revenue comes from subscription fees or pay-per-use credits, targeting individual users and small businesses needing scalable voice messaging solutions.
License this skill as part of a larger communication platform for businesses, integrating it into customer support systems or internal tools. Revenue is generated through licensing fees, custom development, and ongoing support services, focusing on industries like retail, healthcare, or education.
Market the skill to podcasters, educators, or social media influencers for creating and distributing voice content via iMessage. Monetize through one-time purchases, premium voice packs, or affiliate partnerships with ElevenLabs, leveraging the expressive TTS features for engaging audience interactions.
💬 Integration Tip
Ensure ElevenLabs API key and BlueBubbles credentials are securely stored in environment variables, and pre-convert audio to Opus @ 24kHz in CAF format to avoid iMessage compatibility issues.
Scored Jun 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...