Skip to main content

Text-to-Speech & Speech-to-Text Technologies in Thirdlane

Text-to-Speech (TTS) and Speech-to-Text (STT) technologies have become indispensable tools in telephony, particularly in recording voice prompts and transcribing voicemail and recorded calls.

STT plays a crucial role in transcribing voicemail and recorded calls. Gone are the days of painstakingly listening to voicemails and manually jotting down important details. With STT, these voice messages are automatically converted into text, making it easier for employees to quickly review and prioritize follow-up actions. The time-saving advantage of STT not only boosts productivity but also ensures that critical information is never missed or misinterpreted. TTS can be used for recording static or dynamic greetings and voice prompts.

Here is how you use these technologies in Thirdlane.

1) Configure related services in your service provider (Google or AWS) and in Configuration Manager as described in more detail in our documentation.

2) Enable Voice Transcription on individual Tenant and User Extensions level.

Using TTS for recording Greetings and Voice Prompts is described here.

Contact us if your application requires dynamically generated greetings or if you are interested in using speech recognition for more advanced tasks. Use speech recognition where it makes sense, where it can improve user experience, and where it can work reliably. BBC skit Voice Activated Elevator makes it quite clear that providing "buttons" is always a good idea!