Audio Processing

Speech Speed

Control how fast or slow the synthesized speech is delivered using the speed parameter.

Speed Range

PROPERTY	VALUE
Parameter	`speed`
Type	`float`
Minimum	`0.25`
Maximum	`4.0`
Default	`1.0`

Examples

python

TTSConfig(model="zero-indic", voice="Nisha", speed=0.25)   # accessibility
TTSConfig(model="zero-indic", voice="Nisha", speed=1.0)    # normal (default)
TTSConfig(model="zero-indic", voice="Nisha", speed=1.5)    # fast — notifications
TTSConfig(model="zero-indic", voice="Nisha", speed=4.0)    # maximum — batch previews

Tips

For accessibility use cases (screen readers, elderly users), 0.25 to 0.75 improves comprehension.
For notification audio, 1.2 to 1.5 keeps messages concise without losing clarity.
Values above 2.0 are useful for batch previewing large volumes of generated audio.

PreviousChoosing the Right Format Next Silence Trimming