Tag

tts

10 posts.

The TTS Voice setting decides which Cepstral voice reads your text aloud. Here is what it controls and why the default is Allison-8kHz.

Integrating Cepstral TTS with VICIdial means buying three licenses — Voice, Channel, and Save-to-file — each sold on a different basis.

Cepstral is the text-to-speech engine that turns VICIdial prompt text into spoken audio, with SSML control over pronunciation, pitch, and volume.

The TTS ID is the unique short identifier for a Text-to-Speech entry; the TTS Name is the descriptive label. Here is how each one is used.

Replace any campaign audio prompt with a text-to-speech entry by typing TTS followed by the entry id into the audio field.

Drop audio tags into a VICIdial TTS entry to play recorded WAV files alongside spoken lead data inside the same prompt.

SSML lets you tell VICIdial's text-to-speech engine how to say numbers, letters, and account IDs instead of guessing the pronunciation.

Drop lead variables like --A--first_name--B-- into a VICIdial TTS entry to read a caller's own details back to them in the generated audio.

Step-by-step on creating a Text-to-Speech entry in VICIdial, including the three required fields and the prerequisites that make it speak.

Text-to-Speech turns typed text into spoken audio in VICIdial, but it depends on Cepstral being installed and a system setting being enabled.