openclaw-mlx-audioLocal TTS/STT integration for OpenClaw using mlx-audio - Zero API keys, Zero cloud dependency
Install via ClawdBot CLI:
clawdbot install gandli-2025/openclaw-mlx-audioGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
rm -rf ~Calls external URL not in known-safe list
https://github.com/gandli/openclaw-mlx-audioAI Analysis
The skill promotes fully local execution with no API keys or cloud dependencies, aligning with its stated privacy goals. The external GitHub URL is for source code distribution, not data exfiltration, and no credential harvesting or obfuscation patterns are present. The primary risk is the potential for unsafe shell commands during installation, but these require explicit user action.
Audited Apr 16, 2026 · audit v1.0
Generated May 6, 2026
A medical clinic uses OpenClaw MLX Audio to transcribe patient interactions and generate appointment reminders in multiple languages, all on a single Apple Silicon Mac to ensure patient data never leaves the premises.
An online course creator generates high-quality TTS audio for lectures in Chinese, English, and Japanese using the Qwen3-TTS model, then uses STT to verify pronunciation, all locally without cloud costs.
A small podcast team records interviews, uses STT to generate draft transcripts for editing, and clones the host's voice for automated ad reads, running entirely on a Mac Studio for zero cloud dependency.
A nonprofit serving visually impaired users deploys a local TTS system on donated Macs to convert newsletters and forms into speech in multiple languages, with no ongoing API costs.
A boutique law firm builds a local voice bot to handle initial client intakes: STT transcribes queries, TTS reads back relevant information, and all processing stays on-device for confidentiality.
Sell the plugin as part of a premium OpenClaw extension pack. Revenue comes from per-seat licenses for businesses that want local, privacy-first audio processing on Apple Silicon.
Offer fine-tuning or custom voice cloning models for enterprise clients. Revenue from consulting fees to adapt the open-source models for specific accents or industry jargon.
Provide priority support and regular model updates for organizations that rely on the tool in production. Revenue from annual support contracts.
💬 Integration Tip
After installing dependencies via brew and uv, copy the extension folder and configure the JSON in openclaw.json; then simply restart OpenClaw to start using voice commands.
Scored Jun 27, 2026
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.
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。
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...
Create, manage, and deploy ElevenLabs conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.
Voice note transcription and archival for OpenClaw agents. Powered by Deepgram Nova-3. Transcribes audio messages, saves both audio files and text transcript...
Text-to-Speech (TTS) and Speech-to-Text (ASR) using coze-coding-dev-sdk. Returns results directly to stdout.