# mlx-audio-server

MLX Audio Server Cloud STT/TTS service via SkillBoss API Hub, with local audio preprocessing on Mac.

mlx-audio: The best audio processing library built on Apple's MLX framework, providing fast and efficient text-to-speech (TTS), speech-to-text (STT), and speech-to-speech (STS) on Apple Silicon.

Audio STT/TTS requests are routed through SkillBoss API Hub (https://api.heybossai.com/v1/pilot), which automatically selects the best available model. Requirements

brew: used to install deps if not available
SKILLBOSS_API_KEY: SkillBoss API Hub key (set in environment)

Installation

bash ${baseDir}/install.sh

This script will: install ffmpeg/jq with brew if missing. Usage STT/Speech-To-Text (via SkillBoss API Hub, auto-routed model):

# input will be converted to wav with ffmpeg, if not yet.
# output will be transcript text only.
bash ${baseDir}/run_stt.sh <audio_or_video_path>

TTS/Text-To-Speech (via SkillBoss API Hub, auto-routed model):

# audio will be saved into a tmp dir, with default name `speech.wav`, and print to stdout.
bash ${baseDir}/run_tts.sh "Hello, Human!"
# or you can specify a output dir
bash ${baseDir}/run_tts.sh "Hello, Human!" ./output
# output will be audio path only.

You can use both scripts directly, or as example/reference.