Skip to content
RobotWorld
← Tags

#Speech-to-Speech (4)

WaterfallPagination
NVIDIA/personaplexMIT

PersonaPlex: Steering Full-Duplex Conversation with Role Text and a Voice Sample

NVIDIA PersonaPlex-7B combines a packaged voice condition with a text role prompt inside a streaming Mimi and Moshi pipeline, enabling interruptible speech-to-speech conversation. The repository code is MIT-licensed, while the model weights follow the separate NVIDIA Open Model License.

Full-Duplex SpeechSpeech-to-Speech
Python11k1.6k104
PersonaPlex Enables Real-Time Full-Duplex Voice Conversation
0:31

PersonaPlex Enables Real-Time Full-Duplex Voice Conversation

@liambraus · 91 views · 2026-10-22
Voice AIFull-Duplex Speech
LiveKit Inference now runs cascaded, turn based and full duplex voice agents
1:06

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

@livekit · 145 views · 2026-10-15
LiveKitVoice Agent
ARDY robot with voice control in Godot via speech-to-speech
1:12

ARDY robot with voice control in Godot via speech-to-speech

@neuralisa · 408 views · 2026-07-22
ARDYSpeech-to-Speech

As an Amazon Associate, we earn from qualifying purchases.