139 skills found · Page 1 of 5
OpenBMB / MiniCPM OA Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Your Phone
kyutai-labs / MoshiMoshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Standard-Intelligence / Hertz Devfirst base model for full-duplex conversational audio
alumae / Kaldi Gstreamer ServerReal-time full-duplex speech recognition server, based on the Kaldi toolkit and the GStreamer framwork.
dotnet / Nerdbank.StreamsSpecialized .NET Streams and pipes for full duplex in-proc communication, web sockets, and multiplexing
TEN-framework / Ten Turn DetectionTurn detection for full-duplex dialogue communication
FireRedTeam / FireRedChatA Fully Self-Hosted Solution for Full-Duplex Voice Interaction
progrium / DuplexFull duplex modern RPC
nu-dialogue / J MoshiJ-Moshi: A Japanese Full-duplex Spoken Dialogue System
xcc-zach / XtalkX-Talk is an open-source full-duplex cascaded spoken dialogue system framework enabling low-latency, interruptible, and human-like speech interaction with a lightweight, pure-Python, production-ready architecture.
yol / Ethernet MacTri-mode (10/100/1000) full-duplex FPGA ethernet MAC in VHDL
neoremind / Navi PbrpcA protobuf based high performance RPC framework leveraging full-duplexing and asynchronous I/O with netty
Soul-AILab / SoulX DuplugPlug-and-play streaming semantic VAD for real-time full-duplex spoken dialogue systems.
DanielLin94144 / Full Duplex BenchA Benchmark for Evaluating Turn-Taking and Overlap Handling in Full-Duplex Spoken Dialogue Models
posener / H2connHTTP2 client-server full-duplex connection
luispl77 / 433Screen SignalHackerFull duplex 433 MHz Signal jammer, recorder, decoder and hacking multitool device based on ESP32 microcontroller and RFM69HW radios. This version of the device provides an OLED screen and simple UI to navigate menus and different hacks/modes/settings.
noctisynth / Oblivion RsA fast, lightweight, and full duplex secure end-to-end encryption protocol based on ECDHE
ASLP-lab / Easy TurnOpen-Source Turn-Taking Detection Model and Dataset for Full-Duplex Spoken Dialogue Systems
KetsuiLabs / MichiAIMichiAI: A Low Latency, Full Duplex Speech LLM with zero coherence loss
sanowl / LSLM Listening While Speaking Language ModelLSLM implements full duplex modeling in interactive speech language models, based on research by Ma et al. (2024). This project advances human-computer interaction through real-time spoken dialogue capabilities.
