← Back to Videos

A Coffee Kiosk Assistant That Ignores Hijackers

Loading video

A full-duplex audiovisual model tracks who is speaking to the kiosk and rejects attempts by bystanders to hijack an order without directional microphones.

Voice Interaction Audio-Visual AI Speaker Isolation Service robots Kiosk

Category: voice-interaction

Author: @tavus

Date: 2026-11-09T00:00:00

Duration: 68.193s

Source: https://x.com/tavus/status/2119869660502036637

A Full-Duplex AI Persona That Reacts While You Speak

A Full-Duplex AI Persona That Reacts While You Speak

@fangchangma · 31 views · 2026-11-09

Full-Duplex AIAudiovisual Model

PersonaPlex Enables Real-Time Full-Duplex Voice Conversation

PersonaPlex Enables Real-Time Full-Duplex Voice Conversation

@liambraus · 184 views · 2026-10-22

Voice AIFull-Duplex Speech

LivLiv Player Ships a 34 KB Web Avatar

@yeko_L · 117 views · 2026-11-05

Digital HumanWeb Player

A Fully Local Real-Time Voice Avatar

@0xShug0 · 110 views · 2026-11-05

Digital HumanSpeech

Falcon: Visual Target-Speaker Extraction in Noise

Falcon: Visual Target-Speaker Extraction in Noise

@aigclink · 164 views · 2026-10-31

Target Speaker ExtractionAudiovisual Learning

ElevenLabs CLI v1: Voice Workflows in the Terminal

ElevenLabs CLI v1: Voice Workflows in the Terminal

@ElevenLabsDevs · 156 views · 2026-08-25

As an Amazon Associate, we earn from qualifying purchases.