![]() If Vocalizer can't find a complete recording of the requested text, it generates high quality text-to-speech and blends it seamlessly with any partial prompts in your library. With Vocalizer, you provide the text to read and Vocalizer pulls from your library of pre-recorded prompts to assemble the audio output. ![]() Today's applications developers manually keep track of a confusing list of sound clips. Callers who hear "patchwork prompts" of multiple voices with poorer quality text-to-speech are distracted by the mixed voices and are more likely to opt-out of automation. Research has shown that callers are more likely to complete an automated call when they hear information such as names and addresses read clearly by a single voice. Vocalizer's text-to-speech capabilities can read back that information as part of an automated system, saving a transfer to an agent to complete the task. Sometimes a caller needs to hear dynamic information that's tough to pre-record with voice talent such as names, addresses or information from a database.
0 Comments
Leave a Reply. |