Product Launchmlxqwen3 ttsopenclawapple silicon
OpenClaw Adds Local TTS Using MLX-Audio
8.1
The openclaw-mlx-audio plugin provides local text-to-speech for OpenClaw using Apple's MLX framework on Apple Silicon Macs (M1 and later), exposing an OpenAI-compatible /v1 audio endpoint. It supports Kokoro-82M (~345 MB) and Qwen3-TTS variants (0.6B ~2.3 GB, 1.7B ~4.2 GB), bootstraps a managed Python runtime, and offers configurable parameters while requiring initial model downloads and sufficient RAM (8–16+ GB).
Key Points
- 1Provides local TTS endpoint on Apple Silicon via MLX, compatible with OpenAI /v1 audio API
- 2Enables low-latency, offline speech generation using compact Kokoro and Qwen3 model variants
- 3Requires Apple Silicon and 8–16+ GB RAM; choose models based on disk and runtime memory constraints
Scoring Rationale
Practical and official plugin with clear installation and models; limited impact due to Apple Silicon and OpenClaw scope.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
