In Japanese call centers, the Jev and ElevenLabs integration visualizes emotions during calls with colors and six meters, helping to quickly spot dissatisfaction or hesitation hard to detect from words alone.
In Japanese call centers, making it harder to overlook changes in voice. The integration of Jev and ElevenLabs visualizes emotions during calls with colors and six meters. It seems possible to quickly notice dissatisfaction or hesitation that's hard to pick up from words alone,
The author shares a Jev usage insight: it seemed tricky at first, but clicked when framed as 'not letting the AI write text.' Using inquiry handling as an example, the conventional approach dumps everything on GPT or Claude to analyze, while Jev takes a different approach.
The prototype uses AI to estimate hesitation or interest from cursor back-and-forth movements or lingering before clicking, observing customer demeanor and supplementing explanations or suggesting comparisons.
The author built an e-commerce real-time customer service demo using Jev and gpt-live-1, which instantly suggests recommended products based on the user's speech during a conversation, delivering a great experience.
