Feature Requests

This is a feature request (from a Discord user) for the Face model of the Expression Measurement API to return details of the eye color, hair color, skin tone, eye type, and nose shape.

Currently the expression measurement API supports speaker-based diarization (identify_speaker param) only. For use cases where speakers are diarized by channels, we'd have to send each audio channel separately to the API for processing. This requirement is for supporting channel-based diarization.

The use case of using this endpoint as the one way to pipe user mic data in and get everything you need including a raw transcription. The output should have both text transcribed, Word or character level timing boundaries, and the emotional dictionary for each word. It also would be good to support headless pcm data that can be sent in bytes as they arrive. And not have to add headers to each chunk. It should also detect emotion in between spoken words like crying or laughing.

Sometimes our speaker diarization model with the expression measurement API is not accurate. Specifically: sometimes the speaker will always be unknown despite being clearly audible Male and female voices together work great, but having two female or two male voices results in a single speaker being detected While we are not prioritizing this right now because of other priorities, please upvote or comment if you're experiencing similar issues!