supertonic say¶
Generate speech from text and play it directly without saving a file.
Requires sounddevice
This command requires the sounddevice package for audio playback. Install it with: pip install supertonic[playback] or pip install sounddevice
Usage¶
Examples¶
# Basic usage - play speech directly
supertonic say 'Hello, welcome to the world!'
# Use a different voice
supertonic say 'This is a female voice style.' --voice F1
# Adjust speech speed (faster)
supertonic say 'This sentence is spoken at a faster speed than normal.' --speed 1.5
# Higher quality with more steps
supertonic say 'This is a high quality output.' --steps 10
# Use custom voice style
supertonic say 'This is a custom voice test.' --custom-style-path ./my_voice.json
# Verbose mode to see processing details
supertonic say 'Verbose mode shows detailed processing information.' -v
Arguments¶
TEXT¶
Text to synthesize and play
--voice¶
Voice style (default: M1)
Default: M1
--custom-style-path¶
Path to custom voice style JSON file (overrides --voice if provided)
--steps¶
Quality steps (default: 5, higher=better)
Default: 5
--speed¶
Speech speed (0.7-2.0, default: 1.05, 2.0=2x faster)
Default: 1.05
--max-chunk-length¶
Maximum characters per chunk (default: 300)
Default: 300
--silence-duration¶
Silence between chunks in seconds (default: 0.3)
Default: 0.3
-v, --verbose¶
Enable verbose output with detailed logging
Default: False