tts - Local TTS and STT on Apple Silicon
Provides local text-to-speech, speech-to-text, voice cloning, and subtitle generation using Vox CLI on Apple Silicon.
Tags
Updated: 2026-09-23Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Synthesize text to speech
- Transcribe speech to text
- Clone voice from audio sample
- Design voice from text description
- Generate SRT and VTT subtitles
- Batch process text to speech
Inputs
- Text to synthesize
- Audio file
- Reference audio sample
- Text file
- Voice description
Outputs
- Generated WAV audio file
- Transcript text file
- SRT subtitle file
- VTT subtitle file
- JSON transcript file
Requirements
- Apple Silicon Mac (M1/M2/M3/M4)
- macOS 13+
- Python 3.10+
- Vox CLI