LaunchKit · 2026
Back to Skills

local-voice

Local text-to-speech (TTS) and speech-to-text (STT) using FluidAudio on Apple Silicon.

1
1.2k downloads
by @trondw

Setup & Installation

openclaw skills install @trondw/local-voice

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install local-voice

Version History

v1.0.1Feb 8, 2026 - Version note by skill developer:

Minor documentation update

What This Skill Does

Runs text-to-speech and speech-to-text entirely on Apple Silicon using FluidAudio's CoreML models via the Apple Neural Engine. TTS uses the Kokoro model with 54 voices at ~0.6-0.8s latency; STT uses Parakeet TDT v3 with ~0.2-0.3s latency across 25 languages. No network connection or API key required.

Achieves sub-second voice synthesis and transcription on-device, replacing cloud TTS/STT services without API costs, rate limits, or sending audio data off-device.

When to use it

  • Reading long articles aloud while multitasking
  • Transcribing recorded meetings without uploading audio to the cloud
  • Adding offline voice output to a local AI assistant
  • Converting written notes to audio files for listening on the go
  • Building voice interfaces for local automation scripts

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Read this paragraph aloud

AGENT
  1. 1Receives text input from the user
  2. 2POSTs text to the local TTS endpoint at http://127.0.0.1:18790/synthesize
  3. 3StellaVoice daemon processes the request using the Kokoro model on the Apple Neural Engine
  4. 4Returns a WAV file in approximately 0.6-0.8 seconds
  5. 5Plays the audio output to the user
OUTPUT

The paragraph is spoken aloud in the selected Kokoro voice with natural pacing

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

Apple Silicon Mac (M1 or newer) running macOS 14+espeak-ng (install via Homebrew: brew install espeak-ng)