--- title: Kyutai Labs Releases Moshi: A Real-Time Full-Duplex... description: Kyutai Labs has introduced Moshi, a cutting-edge real-time spoken dialogue system featuring full-duplex communication, low latency, and an innovative Inner... canonical: https://daily.dev/posts/kyutai-labs-releases-moshi-a-real-time-full-duplex-dialogue-system-enhancing-human-like-conversatio-7xlwl3gax twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Kyutai Labs Releases Moshi: A Real-Time Full-Duplex Dialogue System Enhancing Human-like Conversations with Low Latency and High Speech Quality | daily.dev og:description: Kyutai Labs has introduced Moshi, a cutting-edge real-time spoken dialogue system featuring full-duplex communication, low latency, and an innovative Inner... og:url: https://daily.dev/posts/kyutai-labs-releases-moshi-a-real-time-full-duplex-dialogue-system-enhancing-human-like-conversatio-7xlwl3gax og:image: https://api.daily.dev/og/posts/7xlWl3GaX.png og:image:alt: Kyutai Labs Releases Moshi: A Real-Time Full-Duplex Dialogue System Enhancing Human-like Conversations with Low Latency and High Speech Quality og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Kyutai Labs Releases Moshi: A Real-Time Full-Duplex Dialogue System Enhancing Human-like Conversations with Low Latency and High Speech Quality **[Collections](https://daily.dev/sources/collections)** · 2 min read · 1 upvotes · 0 comments ## Summary Kyutai Labs has introduced Moshi, a cutting-edge real-time spoken dialogue system featuring full-duplex communication, low latency, and an innovative Inner Monologue method for coherent responses. Integrating Helium language model and Mimi audio codec, Moshi offers efficient audio tokenization and high-quality speech. With open-source code and models, it encourages community contributions for further advancements. ## Content # Kyutai Labs Releases Moshi: An Advanced Real-Time Full-Duplex Dialogue System Kyutai Labs has unveiled Moshi, a groundbreaking real-time spoken dialogue system that offers full-duplex communication. This means both user and system can engage in natural, overlapping conversations, enhancing the fluidity and realism of interactions. ## Key Features - **Full-Duplex Communication**: Moshi allows for natural, overlapping dialogues between the user and the system, dramatically improving interaction smoothness. - **Low Latency**: The system achieves impressively low-latency responses, thanks to its sophisticated architecture and advanced machine learning algorithms. - **Inner Monologue Method**: To ensure coherence and context-aware responses, Moshi employs an innovative Inner Monologue method that predicts text tokens as part of its internal processing. - **Helium Language Model & Mimi Audio Model**: Moshi integrates the specialized Helium language model and the Mimi neural audio codec system, drastically reducing latency and improving speech quality. The Mimi codec processes 24 kHz audio at an efficiency of 1.1 kbps. ## Technical Specifications - **Advanced Machine Learning Algorithms**: The system combines text-to-speech (TTS) and automatic speech recognition (ASR) technologies for seamless real-time interactions. - **Audio Tokenization**: Utilizes the Mimi audio model for efficient audio tokenization and processing. - **Deployment Options**: Moshi can operate on various backends including Python (PyTorch, MLX) and Rust, supporting different models and quantizations. - **User Interface**: Available in interactive mode via web UI or command line interface, catering to diverse user preferences. ## Open Source Release Kyutai Labs has open-sourced the code and models of Moshi, inviting the developer community to experiment and contribute to its further development. This move aims to enhance collaborative innovation and drive the evolution of real-time spoken dialogue systems. Moshi not only sets a new benchmark in conversational AI with its advanced features and low-latency performance but also fosters an open environment for ongoing enhancements in the field. ## Similar posts on daily.dev - [Don’t just attend KubeCon \+ CloudNativeCon, Merge Forward your experience\!](https://daily.dev/posts/don-t-just-attend-kubecon-cloudnativecon-merge-forward-your-experience--l0rpp73x8) · CNCF · 1 upvotes · 0 comments - [Announcing H2 2026 KCDs](https://daily.dev/posts/announcing-h2-2026-kcds-m96goajm1) · CNCF · 1 upvotes · 0 comments - [Two months of Open Community Groups](https://daily.dev/posts/two-months-of-open-community-groups-asf52zhbs) · CNCF · 0 upvotes · 0 comments - [CNCF Unveils Schedule for KubeCon \+ CloudNativeCon Europe 2026](https://daily.dev/posts/cncf-unveils-schedule-for-kubecon-cloudnativecon-europe-2026-ikhcoa5cb) · CNCF · 2 upvotes · 0 comments - [CNCF Debuts KubeCon \+ CloudNativeCon Japan 2026 Schedule](https://daily.dev/posts/cncf-debuts-kubecon-cloudnativecon-japan-2026-schedule-xp5pyudub) · CNCF · 1 upvotes · 0 comments --- Tags: [#ai](https://daily.dev/tags/ai), [#machine-learning](https://daily.dev/tags/machine-learning), [#open-source](https://daily.dev/tags/open-source), [#speech-recognition](https://daily.dev/tags/speech-recognition) [View this post on daily.dev](https://daily.dev/posts/kyutai-labs-releases-moshi-a-real-time-full-duplex-dialogue-system-enhancing-human-like-conversatio-7xlwl3gax) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Kyutai Labs Releases Moshi: A Real-Time Full-Duplex Dialogue System Enhancing Human-like Conversations with Low Latency and High Speech Quality","url":"https://daily.dev/posts/kyutai-labs-releases-moshi-a-real-time-full-duplex-dialogue-system-enhancing-human-like-conversatio-7xlwl3gax","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/kyutai-labs-releases-moshi-a-real-time-full-duplex-dialogue-system-enhancing-human-like-conversatio-7xlwl3gax"},"datePublished":"2024-09-19T03:09:23.593Z","dateModified":"2024-09-19T13:07:51.594Z","description":"Kyutai Labs has introduced Moshi, a cutting-edge real-time spoken dialogue system featuring full-duplex communication, low latency, and an innovative Inner...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/559e7650c4973fb8fc79b1a7ab092bcf?_a=AQAEuiZ","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/559e7650c4973fb8fc79b1a7ab092bcf?_a=AQAEuiZ","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/kyutai-labs-releases-moshi-a-real-time-full-duplex-dialogue-system-enhancing-human-like-conversatio-7xlwl3gax","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai,machine-learning,open-source,speech-recognition","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"Kyutai Labs Releases Moshi: A Real-Time Full-Duplex Dialogue System Enhancing Human-like Conversations with Low Latency and High Speech Quality"}]} ```