Rex retweeted
one API call instead of 10+ audio models
@hume_ai just launched an API that listens to audio the way a person does
you send a voice clip and ask a question in plain english, like:
> how many people are talking?
> is anyone laughing?
> does the caller sound frustrated?
it gives you an answer with a confidence score, no transcript needed
i've always found it weird that voice AI only reads the words. half of what we mean is in how we say it
really clean idea from Hume
馃 Paid partnership
Introducing the Hume Audio Decision API.
Ask anything: How many speakers? Is anyone laughing? Is the caller frustrated?
What used to take 10+ models is now one call.
Trained on 10M+ human judgments, so it answers the way human listeners would.
Realtime, or across hours of recordings.
Request access below.
