Sign in

Repository Index

132,241 visible repositories in the index

Tags: All Tags
Tags

A repository shows when it has any selected Tag.

Filters

Filters

Clear all filters

1–15 of 15 · Most stars

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.

Controllable Transcription. Verbatim ( every, filler, pause, stutter, vocal sound) , or intended ( what the speaker meant to say, optimized for readability) with word-level timestamps.

  • asr
  • audio
  • detection
  • filler

Skyeye云零代码,采用Springboot + UNI-APP + Ant Design Vue的框架的快速开发平台。包含50多种电子流程,CRM、PM、ERP、MES、ADM、OA、EHR、AI、项目、商城、财务、多班次考勤、薪资、招聘、云售后、论坛、问卷、报表设计、工作流、Saas等功能。打造全网首套零代码、功能最全、价格最优惠的智能制造行业供应链一体化管理软件。

Open full-duplex voice models that hear your tone and speak with one. One GPU with vLLM-Omni, or fully offline on a Mac with MLX. Zero-shot voice cloning, OpenAI Realtime / GPT-Live compatible, free hosted API trial. Apache-2.0.

  • full-duplex
  • open-source
  • paralinguistics
  • realtime

A full-duplex real-time interaction system with live audio and vision, continuous conversation, and background tool use.