Audio
FlashLabs-Chroma
Open-source real-time spoken dialogue with personalized voice cloning.
★ 549 starsApache-2.0
View guide →// audio · kyutai-labs/moshi
Moshi
Moshi is an open-source audio project by kyutai-labs (kyutai-labs/moshi on GitHub). It has 11,363 GitHub stars and 1,051 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 9 September 2026.
Moshi — Kyutai full-duplex spoken dialogue model: talk and listen at the same time, ~200ms latency, Apache-2.0
★ 11.4k stars⑂ 1.1k forksApache-2.0updated 2026-09
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- kyutai-labs/moshi
- GitHub stars
- 11,363
- Forks
- 1,051
- License
- Apache-2.0
- Last updated on GitHub
- 9 September 2026
- Category
- Audio
- Listing
- Full install guide
- Official site
- Model weights
// how it works
How it works
- 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.
// features
Why people love it
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
// run it
Run it yourself
- 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
// use cases
What you can build
- 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
// faq
Questions, answered
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.
// keep exploring
Similar tools
Audio
talk-to-fengge
Clone anyone's voice and personality for real-time conversation.
★ 469 starsApache-2.0
View guide →Audio
ChatTTS
A generative speech model built for daily dialogue — natural, conversational text-to-speech
★ 39.9k starsAGPL-3.0
View guide →Audio
MOSS-TTS-Nano
MOSS-TTS-Nano: a 0.1B open multilingual speech model that clones voices and streams in real time on CPU
★ 4.5k starsApache-2.0
View guide →Audio
dia
A TTS model capable of generating ultra-realistic dialogue in one pass.
★ 19.4k starsApache-2.0
View guide →Audio
MOSS-TTS
MOSS-TTS family: open text-to-speech models for voice cloning, dialogue, voice design, and real-time agents
★ 4.2k starsApache-2.0
View guide →// alternatives
Alternatives in Audio
The most-starred other Audio projects in the LibreAI catalogue — the realistic shortlist if Moshi is not the right fit.
- MoneyPrinterTurbo★ 128.3k
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★ 109.9k
Robust Speech Recognition via Large-Scale Weak Supervision
- GPT-SoVITS★ 62.3k
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- Real-Time-Voice-Cloning★ 60.2k
Clone a voice from 5 seconds of audio and generate arbitrary speech in real time
- whisper.cpp★ 54.1k
Port of OpenAI's Whisper model in C/C++
// more in audio
More in Audio
Nearby Audio projects in the catalogue, closest in stars to Moshi — keep exploring the shelf either side of it.
- speechbrain★ 11.9k
A PyTorch-based Speech Toolkit
- xiaozhi-esp32-server★ 10.8k
Self-hosted backend that gives ESP32 'Xiaozhi' devices streaming voice chat, memory and tool control.
- edge-tts★ 12.2k
Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key
- pyannote-audio★ 10.6k
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
- PaddleSpeech★ 12.7k
Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text…
- silero-vad★ 10.3k
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
Get Moshi
Free and open — grab the source, star the repo, and start creating.