v1

latestOpenAPI 3.0.02026-07-17303.1 KB

Speak text to WAV

get/api/tts

textstring required

Example:Welcome to the world of speech synthesis!

Text to speak

voicestring

Example:en_UK/apope_low

Voice in the form <lang>/<name>_<quality> optional with #<speaker> at the end

noiseScalenumber

Example:0.667

Volatility of speaker (0-1, default: 0.667)

noiseWnumber

Example:0.8

Volatility of individual phonemes (0-1, default: 0.667)

lengthScalenumber

Example:1

Speed of speaker (default: 1.0, faster < 1 < slower)

ssmlboolean

Input text is SSML

audio

All 3 operations