voice-memo
Send native iMessage voice bubbles with ElevenLabs TTS via BlueBubbles. Use when: user asks to send a voice message, wants something spoken aloud, storytelling or summaries requested, or voice delivery would be more engaging than text. Requires ElevenLabs API key and BlueBubbles.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/amzzzzzzz/imessage-voice-memo-skillWhat This Skill Does
The Voice Memo skill enables your OpenClaw agent to send native iMessage voice bubbles rather than standard text or file attachments. By integrating ElevenLabs' high-quality text-to-speech engine with the BlueBubbles private API, this skill allows for natural, expressive, and human-like voice communication directly within your Apple ecosystem. It handles the complex task of audio synthesis, conversion to the iMessage-native Opus CAF format at 24kHz, and routing through the private API to ensure the messages appear as authentic audio bubbles in your conversation history.
Installation
To begin, ensure you have BlueBubbles running locally on a macOS device with the Private API enabled. Install the skill using the command: clawhub install openclaw/skills/skills/amzzzzzzz/imessage-voice-memo-skill. Configure your ~/.openclaw/.env file by adding your ELEVENLABS_API_KEY and BLUEBUBBLES_PASSWORD. You may optionally define ELEVENLABS_VOICE_ID and ELEVENLABS_MODEL_ID to customize the agent's persona. The skill relies on macOS system utilities like afconvert to handle audio transformation; verify these are accessible in your environment path. Always confirm that your chatGuid is formatted as any;-;+PHONE to bypass common iMessage API timeout issues.
Use Cases
Use this skill whenever you want to convey emotion or tone that text cannot capture. It is ideal for sending quick, informal updates to friends, delivering summaries or storytelling sessions where a voice narration feels more engaging, or simply when a user explicitly requests a voice message. This skill is particularly useful for users with visual impairments or those who prefer audio-first communication workflows.
Example Prompts
- "Send a voice message to Sarah saying that I'm running ten minutes late but I'm really looking forward to dinner."
- "Summarize the article I just sent to John, but send it as a voice note so he can listen while he drives."
- "Tell my brother in a voice memo that I got the promotion! [excited] I'm so happy!"
Tips & Limitations
Note that native voice bubbles require the Private API to function correctly; if a message arrives as an attachment, re-verify your configuration settings. The quality of the voice is dependent on the selected ElevenLabs model; while the default Rachel voice is highly natural, you can experiment with expressive tags like [sighs] or [laughs] to add personality. Be aware that while incoming voice memos are transcribed for your agent's context, these transcripts are not stored long-term unless you specifically instruct the agent to save them to your memory files.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-amzzzzzzz-imessage-voice-memo-skill": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, external-api