Search Results for "duplex"

Qwen Audio Agent is a real-time voice runtime designed to keep an AI assistant conversationally present while it performs longer tasks. It supports full-duplex speech, natural interruption, and continuous multi-turn dialogue. Direct questions are answered immediately, while tool-intensive work can be delegated to a background coding agent without ending the voice session. Users can start several independent tasks, check progress, cancel work, and continue discussing returned results. The system can reuse an agent’s existing tools, MCP servers, skills, configuration, and authentication through ACP-based integrations. ...

PersonaPlex is an open-source real-time conversational speech AI model that goes beyond traditional text chat by providing full-duplex speech-to-speech interaction, meaning it can listen and talk at the same time instead of waiting for you to finish speaking before responding. This architectural approach eliminates awkward pauses and makes conversations feel much more human-like, with natural behaviors such as overlapping speech, interruptions, and fluent turn-taking, traits that traditional AI assistants typically lack. ...

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec. Mimi processes 24 kHz audio, down to a 12.5 Hz representation with a bandwidth of 1.1 kbps, in a fully streaming manner (latency of 80ms, the frame size), yet performs better than existing, non-streaming, codecs like SpeechTokenizer (50 Hz, 4kbps), or SemantiCodec (50 Hz, 1.3kbps).

Visit NAPS2's home page at www.naps2.com. NAPS2 is a document scanning application with a focus on simplicity and ease of use. Scan your documents from WIA- and TWAIN-compatible scanners, organize the pages as you like, and save them as PDF, TIFF, JPEG, PNG, and other file formats. Available on Windows, Mac, and Linux. NAPS2 is currently available in over 40 different languages. Want to see NAPS2 in your preferred language? Help translate! See the wiki for more details.

...It can be easily integrated as a microservice into neural search solutions. Serve CLIP models with TensorRT, ONNX runtime and PyTorch w/o JIT with 800QPS[*]. Non-blocking duplex streaming on requests and responses, designed for large data and long-running tasks. Horizontally scale up and down multiple CLIP models on single GPU, with automatic load balancing. Easy-to-use. No learning curve, minimalist design on client and server. Intuitive and consistent API for image and sentence embedding. Async client support. ...

Scene Warez Groups Distro Downloader Categories Anime Applications Android iOS MAC Tutorials Windows Ebooks Comics eBook Magazines Games Linux MAC PC PS3 PSP Wii XBOX360 Movies BDRiP Cam DVDRiP DVDRiP Old DVDSCR HDRiP R5 RC SCR Staff Picks Telecine Telesync Workprint Tech News TV Shows TV Packs Albums iTunes MViD Singles/EPs Staff Picks Scene Groups Distro Access: rG - ECZ - P2P - PLAZA - TE - CPY - FANiSO - ZEKE - 3DM - ALiAS - DVT - DVTISO - ACTiVATED - POSTMORTEM - DUPLEX - BiTE - PROPHET - CODEX - RELOADED -SKIDROW - RAZOR1911 - FTS - FLT - CORE - BAT - HI2U - SMACKs - MONEY - DEFA - DOGE - NEWiSO - TBE - MAGNiTUDE -

ScanTWAIN is an Open Source TWAIN production quality scanning application based on QT 3.x. ScanTWAIN allows for duplex scanning from automatic document feeder (ADF) based scanners via TWAIN.

Unmaintained! Remuco is a duplex remote control system for Linux media players and mobile phones using Bluetooth or WiFi.

WARNING: THIS PROJECT IS OBSOLETE NOW, check the recent version at https://sourceforge.net/projects/naps2/ This software makes scanning of documents (including from ADF and Duplex) as simple as possible. Requires .NET Framework 2.0

Steganography tool which establishes a full-duplex steganographic data transfer protocol utilizing Real-time Transfer Protocol (RTP) packet payloads as the cover medium. The tool provides interactive chat, file transfer, and remote shell access.

Multitrack is a program that uses the harddisk for recording. It can record two to sixteen tracks. It supports two wavedevices or one full-duplex device for simultaneous playback and recording of sound.