An Openclaw Skills extension that uses local Kokoro TTS to send authentic, waveform-enabled iMessage voice messages.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install imessage-voice-reply
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install imessage-voice-reply using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is iMessage Voice Reply?
The iMessage Voice Reply skill allows developers to integrate high-quality, local text-to-speech capabilities into their messaging workflows. By utilizing Openclaw Skills, this tool generates native voice bubbles that include the signature iMessage waveform and inline playback functionality, rather than sending generic file attachments. This is achieved through the Kokoro-ONNX engine and macOS native encoding, ensuring privacy and zero operational costs. This skill is particularly useful for maintaining the flow of voice-to-voice conversations within the Apple ecosystem without requiring manual recording.
iMessage Voice Reply Use Cases
- Reslying to incoming voice memos in iMessage to maintain a consistent voice-for-voice interaction.
- Sending hands-free audio responses when the recipient is in a situation where listening is easier than reading.
- Automating personalized notifications or updates that feel more human and native to the recipient's device through Openclaw Skills.
How iMessage Voice Reply Works
- The AI agent generates a text response based on the conversation context.
- The text is passed to the local Kokoro-ONNX TTS engine to synthesize high-quality audio.
- The skill uses the macOS native afconvert utility to encode the audio into a CAF container with the Opus codec.
- The processed file is sent via the BlueBubbles bridge with specific flags (asVoice=true) to identify it as a voice message.
- iMessage renders the message as a native interactive bubble with a visible waveform.
iMessage Voice Reply Setup
To install the necessary dependencies and download the local models, run the following command:
bash ${baseDir}/scripts/setup.sh
This setup script configures kokoro-onnx and the required Python environment. You must also have a BlueBubbles channel configured within your Openclaw Skills settings to handle the message delivery.
iMessage Voice Reply Data Schema & Taxonomy
The skill manages audio data and metadata according to the following schema to ensure native rendering:
| Attribute | Value / Requirement |
|---|---|
| Container | CAF (Core Audio Format) |
| Codec | Opus (48kHz mono, 32kbps) |
| MIME Type | audio/x-caf |
| Filename | Must be set to Audio Message.caf |
| Model Storage | Models are stored locally in ~/.cache/kokoro-onnx/ |
| Platform | Native encoding requires macOS; Linux uses ffmpeg/MP3 fallback |
iMessage Voice Reply Advanced Features
- Support for multiple languages including English, Spanish, French, Japanese, and Chinese using specific Kokoro voice models.
- Custom playback speed controls (default 1.15x) to optimize the listening experience.
- Intelligent silence padding to ensure audio is not clipped during the initial seconds of playback.
- Completely local processing within Openclaw Skills to maintain data privacy and eliminate external API subscription costs.
SKILL.md
Loading
Related Openclaw Skills
Proton Bridge Email (age-encrypted)
A secure email automation tool for sending messages via Proton Mail Bridge using age-encrypted credentials.
Modular Market Brief
A configurable AI skill for generating modular, data-driven global market briefs across equities, crypto, and commodities.
Colormind
A technical tool for generating professional color palettes and extracting color schemes from images via the Colormind.io API.
Speech-to-Text (STT) Skill
A high-performance audio processing utility that leverages OpenAI Whisper to convert diverse audio formats into accurate text transcriptions.
Coder Helper Skill
An AI-powered utility that converts natural language requirements into documentation and automatically launches your development environment.
A-Share Stock Trader
A comprehensive A-share paper trading system for automated data fetching, strategy backtesting, and portfolio simulation.
METADATA
Featured*
