qwen3-audio - High-performance audio library for Apple Silicon
High-performance audio library for Apple Silicon with text-to-speech and speech-to-text
Tags
Updated: 2026-03-21Capabilities
Typical Inputs
Typical Outputs
What this skill does
- convert text to speech
- clone voice from audio
- create voice from text
- control voice emotion
- transcribe audio to text
- create voice profile
- list voice profiles
- use saved voice
Inputs
- text
- audio file
- voice ID
- speaker name
- language setting
- emotion instruction
Outputs
- audio file
- transcription text
- subtitle file
- voice profile
Requirements
- Python 3.10+
- Apple Silicon Mac (M1/M2/M3/M4)