speakturbo-tts

SKILL.md

Ultra-fast text-to-speech with ~90ms latency and 8 built-in voices.

Delivers audio in approximately 90ms after daemon warmup, with first run taking 2-5 seconds for model initialization

Includes 8 pre-configured voices (alba, marius, javert, jean, fantine, cosette, eponine, azelma) accessible via simple command-line flags

Supports file output with configurable directory allowlisting, quiet mode, and UTF-8 text input including long-form content

Auto-starting daemon with 1-hour idle shutdown; use the speak skill instead for voice cloning and emotion tags

speakturbo - Talk to your Claude!

Give your agent the ability to speak to you real-time. Ultra-fast text-to-speech with ~90ms latency and 8 built-in voices.

Quick Start

# Play immediately - you should hear "Hello world" through your speakers
speakturbo "Hello world"
# Output: ⚡ 92ms → ▶ 93ms → ✓ 1245ms

# Verify it's working by saving to file
speakturbo "Hello world" -o test.wav
ls -lh test.wav  # Should show ~50-100KB file

Output explained: ⚡ = first audio received, ▶ = playback started, ✓ = done

First Run