kyutai-labs / moshi
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.
☆7,506Updated last week
Alternatives and similar repositories for moshi:
Users that are interested in moshi are comparing it to the libraries listed below
- LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve spee…☆2,809Updated 3 months ago
- A fast multimodal LLM for real-time voice☆3,589Updated last week
- Speech To Speech: an effort for an open-sourced and modular GPT4-o☆3,753Updated 2 months ago
- Inference and training library for high-quality TTS models.☆5,025Updated 2 months ago
- Fast and accurate automatic speech recognition (ASR) for edge devices☆2,564Updated 2 weeks ago
- open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming…☆3,148Updated 3 months ago
- Open Source framework for voice and multimodal conversational AI☆4,778Updated this week
- Local realtime voice AI☆2,224Updated this week
- first base model for full-duplex conversational audio☆1,707Updated last month
- g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains☆4,179Updated 3 weeks ago
- tiny vision language model☆7,409Updated 2 weeks ago
- Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junio…☆8,508Updated 2 weeks ago
- SGLang is a fast serving framework for large language models and vision language models.☆10,325Updated this week
- High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.☆5,578Updated last month
- Zero-Shot Speech Editing and Text-to-Speech in the Wild☆8,121Updated 7 months ago
- Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"☆9,735Updated this week
- A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcri…☆5,920Updated this week
- StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models☆5,465Updated 6 months ago
- Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.☆10,766Updated this week
- Letta (formerly MemGPT) is a framework for creating LLM services with memory.☆14,565Updated this week
- Run PyTorch LLMs locally on servers, desktop and mobile☆3,506Updated this week
- Build real-time multimodal AI applications 🤖🎙️📹☆5,110Updated this week
- Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sag…☆17,763Updated this week
- A language model programming library.☆5,614Updated this week
- SOTA Open Source TTS☆19,207Updated this week
- Blazingly fast LLM inference.☆5,064Updated this week
- GLM-4-Voice | 端到端中英语音对话模型☆2,669Updated 2 months ago
- Foundational model for human-like, expressive TTS☆4,035Updated 6 months ago
- An Open Source text-to-speech system built by inverting Whisper.☆4,120Updated 2 months ago
- 🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.☆11,162Updated this week