Voice Step
Using voice as input when executing a task is becoming increasingly more useful and also more requested, with the use of AI.
To make this experience smooth and seamless we would need a voice step which automatically or on demand (by pressing a button) starts a recording. The recording can be paused or stopped (or auto stopped after a defined number of seconds of relative silence). The recoding is then returned to the workflow and can be processed in the following steps, using AI.
Petter Larsson
shared this idea
-
Johannes Steger
commented
i mean this is possible in the App as all mobile devices have voice to text. It would be nice to see it as an automtic version as mentioned or in webclient as well for sure. We built simple demos with voice to text -> Ai to structured data models and it works great.