Block unveils Dessa, an AI voice model to detect emotions and sarcasm
In brief
- Dessa analyzes audio directly without text conversion to capture emotions and pauses.
- The model runs locally on a MacBook Pro M4 Max but remains unavailable to the public.
- Block aims to overcome the limitations of text-based models with this approach.
Block, the company behind Square and Cash App, has introduced Dessa, a speech model that processes audio directly instead of converting it to text first. According to the announcement, the model runs locally on a MacBook Pro M4 Max but is not yet publicly available.
What it changes for you
- Marketing & AdvertisingVoice analysis tools could better capture real-time emotional reactions from consumers.
This summary gives you the essentials. The full article, its figures and quotes are on The Decoder.
Read the original articleAI-generated summary of the source, checked by rules. How we write · Report an error