Áudio
FlashLabs-Chroma
Open-source real-time spoken dialogue with personalized voice cloning.
★ 549 estrelasApache-2.0
Ver o guia →// audio · kyutai-labs/moshi
Moshi
Moshi é um projeto de áudio de código aberto de kyutai-labs (kyutai-labs/moshi no GitHub). Tem 11.363 estrelas no GitHub e 1.051 forks, é publicado sob a licença Apache-2.0 e foi atualizado pela última vez no GitHub em 9 de setembro de 2026.
Moshi — Kyutai full-duplex spoken dialogue model: talk and listen at the same time, ~200ms latency, Apache-2.0
★ 11,4 mil estrelas⑂ 1,1 mil forksApache-2.0atualizado set 2026
▦ visual: o README deste projeto não inclui nenhuma captura incorporável,
então aqui vai um marcador. O guia abaixo está completo mesmo assim.
então aqui vai um marcador. O guia abaixo está completo mesmo assim.
// dados do projeto
Dados do projeto
- Repositório
- kyutai-labs/moshi
- Estrelas no GitHub
- 11.363
- Forks
- 1.051
- Licença
- Apache-2.0
- Última atualização no GitHub
- 9 de setembro de 2026
- Categoria
- Áudio
- Tipo de ficha
- Guia de instalação completo
- Site oficial
- Model weights
// como funciona
Como funciona
- Install Moshi
Install the PyTorch package from PyPI, or the MLX package on Apple Silicon.
- Start the server
Run the Moshi server, optionally with a Gradio tunnel, pointed at the Moshika weights.
- Talk to it locally or from a client
Run the local MLX client with 4-bit or 8-bit quantisation, or connect the Python client to your server.
// recursos
Por que as pessoas gostam tanto
Full-duplex dialogue
Speaking and listening happen simultaneously — interruptions and overlap work the way real conversation does.
Streaming neural audio codec
Mimi streams 24 kHz audio down to a 12.5 Hz representation at 1.1 kbps, with only 80ms of frame latency.
Low practical latency
Around 200ms overall on an L4 GPU — fast enough for natural spoken interaction.
PyTorch and Apple Silicon routes
A PyTorch server path and an MLX local path with quantised weights for Macs.
Advertisement
// execute você mesmo
Execute você mesmo
- Install (PyTorch)
The README install route from PyPI.
pip install -U moshi - Run locally on Apple Silicon
The README MLX route with 4-bit quantised weights.
python -m moshi_mlx.local -q 4 - Start the server
The README server route, with the Moshika PyTorch weights.
python -m moshi.server --hf-repo kyutai/moshika-pytorch-bf16
// casos de uso
O que você pode criar
- Building voice assistants that handle interruption and overlap
- Real-time spoken dialogue apps with low latency
- Running a full-duplex voice model locally on Apple Silicon
- Studying streaming speech models and neural audio codecs
Advertisement
// perguntas frequentes
Perguntas frequentes
Who makes Moshi?
Kyutai, as a speech-text foundation model and full-duplex dialogue framework.
Is Moshi free?
Yes — Apache-2.0 licensed.
What does full-duplex mean?
The model listens while it speaks, so you can interrupt it and it can overlap — unlike turn-based voice assistants that wait for silence.
How fast is it?
Theoretical latency 160ms, practical overall latency as low as 200ms on an L4 GPU, via the Mimi streaming codec.
How do I get started?
pip install moshi (or moshi_mlx on Apple Silicon), then run the server or the local client.
// continue explorando
Ferramentas semelhantes
Áudio
talk-to-fengge
Clone anyone's voice and personality for real-time conversation.
★ 469 estrelasApache-2.0
Ver o guia →Áudio
ChatTTS
A generative speech model built for daily dialogue — natural, conversational text-to-speech
★ 39,9 mil estrelasAGPL-3.0
Ver o guia →Áudio
MOSS-TTS-Nano
MOSS-TTS-Nano: a 0.1B open multilingual speech model that clones voices and streams in real time on CPU
★ 4,5 mil estrelasApache-2.0
Ver o guia →Áudio
dia
A TTS model capable of generating ultra-realistic dialogue in one pass.
★ 19,4 mil estrelasApache-2.0
Ver o guia →Áudio
MOSS-TTS
MOSS-TTS family: open text-to-speech models for voice cloning, dialogue, voice design, and real-time agents
★ 4,2 mil estrelasApache-2.0
Ver o guia →// alternativas
Alternativas em Áudio
Os outros projetos de Áudio com mais estrelas no catálogo do LibreAI — a lista realista de alternativas se Moshi não for o ideal para você.
- MoneyPrinterTurbo★ 128,3 mil
利用 AI 大模型和自动化工作流，根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with an automated AI workflow.
- Whisper★ 109,9 mil
Robust Speech Recognition via Large-Scale Weak Supervision
- GPT-SoVITS★ 62,3 mil
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- Real-Time-Voice-Cloning★ 60,2 mil
Clone a voice from 5 seconds of audio and generate arbitrary speech in real time
- whisper.cpp★ 54,1 mil
Port of OpenAI's Whisper model in C/C++
// mais em audio
Mais em Áudio
Projetos de Áudio próximos no catálogo, os mais próximos em estrelas de Moshi: continue explorando dos dois lados dele.
- speechbrain★ 11,9 mil
A PyTorch-based Speech Toolkit
- xiaozhi-esp32-server★ 10,8 mil
Self-hosted backend that gives ESP32 'Xiaozhi' devices streaming voice chat, memory and tool control.
- edge-tts★ 12,2 mil
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key
- pyannote-audio★ 10,6 mil
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
- PaddleSpeech★ 12,7 mil
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text…
- silero-vad★ 10,3 mil
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
Baixe o Moshi
Grátis e aberto: pegue o código-fonte, dê uma estrela no repositório e comece a criar.