Generate speech
Authentication
Request
Select Standard or Fast. Append :free for Free access.
Complete text. Surrounding whitespace is removed, then the result must contain 1–2,048 Unicode code points.
Use normal capitalization and punctuation; all-lowercase or unpunctuated text can severely degrade speech quality.
The voice used to generate speech.
Language of the selected voice. Currently supports en.
auto uses the voice’s language, rather than detecting the input language.
false returns audio after generation finishes; true sends audio as it is generated.
Send the complete text in one request in either mode.
wav includes a WAV header; pcm returns raw audio samples.
Both formats support streaming.