Skip to main content

Synthesise a text into an audio file

POST 
/api/v1/audios/tts

Turns a text into speech and stores it in your library, ready to be used by a campaign.

Synchronous: the response comes back only once the audio is really stored, so what you get is immediately playable. Use previewUrl to listen to the result before broadcasting it — on a synthesis this is the one moment where a mispronunciation can be caught before thousands of calls go out.

Submitting a text that was already synthesised for your account reuses the existing audio instead of producing a new one; the response then carries cached: true. The comparison is made on the normalised text, so repeated spaces and line breaks do not create a new synthesis. On a reuse the audio keeps the title of its first synthesis.

Required capability: TTS

Request​

Responses​

The audio has been synthesised and filed.