Text-to-Speech

TTS commands for generating speech from text

Text-to-Speech (TTS)

Commands

Synthesize Speech from Text

60db tts:synthesize --text "Hello this is devendra" --voice-id "voice_id_here"

Specify Output File

60db tts:synthesize --text "Hello world" --voice-id "abc123" --output speech.mp3

Adjust Speech Parameters

60db tts:synthesize --text "Hello" --voice-id "abc123" --speed 1.2 --pitch 0.5 --stability 0.8

List Available Voices

60db tts:voices

Options

• -t, --text <text> - Text to synthesize (required)
• -v, --voice-id <id> - Voice ID to use (required)
• -o, --output <file> - Output audio file path (default: tts_<timestamp>.mp3)
• --speed <number> - Speech speed (default: 1)
• --pitch <number> - Speech pitch (default: 0)
• --stability <number> - Speech stability (default: 1)
• --boost-volume <boolean> - Boost volume (default: false)

Examples

TTS - Generate Speech

# Generate speech from text
60db tts:synthesize --text "Hello, this is devendra" --voice-id "1a8c6331-c79b-47d3-9893-09160a245a3e"

# List available voices first
60db tts:voices

# Save to specific file
60db tts:synthesize --text "Welcome to our service" --voice-id "abc123" --output welcome.mp3