← Back to Videos

Falcon: Visual Target-Speaker Extraction in Noise

Loading video

Falcon is a visual target-speaker extraction model for noisy multi-speaker scenes, with real-time separation and meeting-app integration.

Target Speaker Extraction Audiovisual Learning Speech Separation Real-Time

Category: voice-interaction

Author: @aigclink

Date: 2026-10-31T00:00:00

Duration: 56.238s

Source: https://x.com/aigclink/status/2116410041767194823

Reference: https://github.com/JusperLee/Falcon

Tavus Griffin: the first model to pass the video Turing test — 48% of live callers thought it was human

Tavus Griffin: the first model to pass the video Turing test — 48% of live callers thought it was human

@tavus · 688 views · 2026-10-01

PersonaPlex Enables Real-Time Full-Duplex Voice Conversation

PersonaPlex Enables Real-Time Full-Duplex Voice Conversation

@liambraus · 109 views · 2026-10-22

Voice AIFull-Duplex Speech

ElevenLabs CLI v1: Voice Workflows in the Terminal

ElevenLabs CLI v1: Voice Workflows in the Terminal

@ElevenLabsDevs · 102 views · 2026-08-25

LiveKit Inference now runs cascaded, turn based and full duplex voice agents

LiveKit Inference now runs cascaded, turn based and full duplex voice agents

@livekit · 154 views · 2026-10-15

LiveKitVoice Agent

ElevenLabs introduces the Video to Music API

ElevenLabs introduces the Video to Music API

@ElevenLabsDevs · 140 views · 2026-10-15

ElevenLabsVideo to Music

BaoCut: Open-Source AI Bilingual Subtitle Translation

BaoCut: Open-Source AI Bilingual Subtitle Translation

@dotey · 162 views · 2026-10-14

BaoCutSubtitle Translation

As an Amazon Associate, we earn from qualifying purchases.