skills.rest
appautomatonappautomatonOfficial·6 Agent Skills Included

mlx-speech

Local speech synthesis, cloning, and transcription on Apple Silicon

Runs text-to-speech, voice cloning, audio editing, and speech-to-text entirely on Apple Silicon using pure MLX. Eliminates cloud APIs, PyTorch dependencies, and manual model conversion with ready-to-load local checkpoints. Includes stage-gated planning skills that frame, plan, execute, and verify coding work automatically.
37|7
↗
npx skills add appautomaton/mlx-speech --all -g -y
Available:

Directs the agent through a stage-gated frame-plan-execute-verify workflow, enforcing pure-MLX runtime rules, dependency limits, and tiered test requirements before reporting work complete.

All Skills in This Repository (6)

Pure Emerald Level Indicators
📦 In Repo
appautomatonappautomaton

auto-verify

Verify completed project plans against acceptance criteria via command execution.

Official
Advanced
📦 In Repo
appautomatonappautomaton

auto-frame

Transform user requests into bounded SPEC.md project specifications.

Official
Advanced
📦 In Repo
appautomatonappautomaton

auto-eng-review

Validate technical implementation plans for architectural integrity, safety, and operational risk.

Official
Advanced
📦 In Repo
appautomatonappautomaton

auto-execute

Orchestrate approved project plan slices via direct execution or subagent dispatch.

Official
Advanced
📦 In Repo
appautomatonappautomaton

auto-plan

Convert project specifications into ordered, verifiable execution slices.

Official
Advanced
📦 In Repo
appautomatonappautomaton

auto-resume

Reconstruct project context and execution state from git history and state files.

Official
Advanced

Frequently Asked Questions

FAQPage Schema
How to install mlx-speech?▼

Run `npx skills add appautomaton/mlx-speech --all -g -y` in your terminal to install all skills in this suite globally.

How to run text-to-speech locally on a Mac?▼

Load a model like fish-s2-pro or vibevoice through the Python API or CLI, and it generates waveform audio entirely on your Apple Silicon chip with no cloud calls.

Can mlx-speech clone voices and edit audio?▼

Yes. Models like Fish S2 Pro, Step-Audio-EditX, and dots.tts support voice cloning from a reference clip, emotion tags, and audio editing.

Does mlx-speech support speech-to-text transcription?▼

Yes. It includes multilingual ASR models such as Cohere Transcribe, Qwen3-ASR, Granite Speech, and a streaming Nemotron model for incremental transcription.

What do the auto-plan and auto-execute skills do?▼

They turn an approved request into ordered, verifiable work slices, then implement and test each slice automatically with per-slice commits and a final independent verification pass.

Related Repositories in Software Engineering

View All in Software Engineering→
openclawopenclaw
388.4k

openclaw

Run a personal AI assistant across your devices and chat apps

Official📦 120 Skills
obraobra
280.0k

superpowers

Gives coding agents a disciplined workflow from idea to merged code

Community📦 15 Skills
facebookfacebook
248.4k

react

AI agent skills for building, testing, and porting React core

Official📦 14 Skills