The text-to-speech is a great feature addition. Please consider the next evolution of this approach and integrate Speech Synthesis Markup Language (SSML) for greater control over the nuances of errored interpretation by the AI generator. SSML uses XML tagging to provide instructions to the AI generator to better interpret the text being converted. In the government space, this is a typical ask. In addition, integration with Murf AI would also be a solid upgrade.
Thanks!