Skip to main content
📖 The AI Tool Bible
Kyutai Moshi preview image
Kyutai Moshi logo

Kyutai Moshi

Not yet source-checked

Open-source, full-duplex speech-to-speech foundation model with sub-200ms latency

Machine-drafted from the vendor's site · not yet source-checkedProfile updated Link checked How we rate

Free· Free and open source. Models under CC-BY 4.0, code under MIT (Python) / Apache 2.0 (Rust). Self-hosted only — you pay your own compute (24GB+ GPU for PyTorch, or Apple Silicon via MLX).AudioMoshi (7B-class speech-text foundation model) + Mimi neural audio codec, in-house by Kyutai

In short

Moshi is an open-source, full-duplex speech model by Kyutai offering sub-200ms latency. It runs self-hosted on your own GPU or Apple Silicon with no API costs.

Best for

Researchers, voice-AI engineers and indie teams who need a self-hosted, low-latency spoken-dialogue model with open weights and no per-minute API costs.

Skip if

Product teams that want a managed voice API, multilingual coverage out of the box, or GPT-4o-level knowledge and reasoning wrapped in speech.

Moshi is a speech-text foundation model released by the French non-profit AI lab Kyutai for real-time, full-duplex spoken dialogue. Unlike traditional voice assistants that pipeline ASR to an LLM to TTS, Moshi natively processes two continuous audio streams — the user's microphone and its own synthesized speech — while simultaneously predicting text tokens as an 'inner monologue' that grounds what it says. The result is a conversational voice model that can be interrupted, back-channel ('mm-hmm'), talk over the user, and respond with roughly 200ms of end-to-end latency on an L4 GPU, well below the human turn-taking threshold. The stack includes Mimi, a neural audio codec that compresses 24kHz speech to a 1.1kbps stream at 12.5Hz with 80ms frame latency and outperforms competing streaming codecs. Two fine-tuned voice variants ship: Moshiko (male synthetic voice) and Moshika (female). Weights are available in PyTorch (bf16, int8), MLX (int4/int8/bf16 for on-device Mac and iPhone inference), and a Rust/Candle backend intended for production deployments. Typical workflows are running the browser UI with built-in echo cancellation for demos and research, embedding the Rust server behind a WebSocket for latency-sensitive voice apps, or using MLX to prototype on-device voice interactions on Apple Silicon. Because everything is open weights under permissive licenses, Moshi is best suited to researchers exploring duplex speech modeling, engineers building low-latency voice interfaces without sending audio to a third-party API, and teams that need to fine-tune or study the internals of a full speech dialogue system.

Editor's take

Moshi is the most interesting open release in real-time voice AI — genuinely full-duplex, sub-200ms, and permissively licensed. It won't replace GPT-4o Voice for consumer polish, but if you care about owning your voice stack or studying how duplex speech models actually work, nothing else in the open ecosystem comes close.

— The AI Tool Bible editorial team

Pros

  • ✅ Truly full-duplex — handles interruptions, overlap and back-channels rather than rigid turn-taking
  • ✅ Sub-200ms practical latency on a single L4 GPU, well below third-party voice APIs
  • ✅ Fully open weights (CC-BY 4.0) plus MIT/Apache code — self-host with no per-minute billing
  • ✅ Ships with Mimi, a streaming neural audio codec that beats SpeechTokenizer and SemantiCodec
  • ✅ Multiple inference backends: PyTorch for research, Rust/Candle for production, MLX for on-device Mac/iPhone
  • ✅ Inner-monologue text prediction gives you a transcript alongside the audio stream for free

Cons

  • ⚠️ English-only voices at launch — no multilingual support out of the box
  • ⚠️ Knowledge and reasoning quality trail top text LLMs; it's a 7B-class model, not GPT-4o Voice
  • ⚠️ Requires a 24GB+ GPU for the reference PyTorch build; on-device is only viable via MLX on Apple Silicon
  • ⚠️ No hosted API or SaaS tier — you own the ops, scaling and safety filtering
  • ⚠️ Only two fixed synthetic voices (Moshiko/Moshika); no voice cloning or speaker conditioning in the release

Facts

Open source
Yes
Model used
Moshi (7B-class speech-text foundation model) + Mimi neural audio codec, in-house by Kyutai
Hacker News
12 stories · top 635 points · last Oct 16, 2026 · checked Nov 14, 2026

Where this tool sits

Use cases

Real-time voice assistant prototypesResearch on full-duplex spoken dialogueOn-device voice interaction on Apple Silicon via MLXLow-latency conversational agents behind WebSocketNeural audio codec experimentation with MimiSelf-hosted voice interface for privacy-sensitive appsSpeech tokenizer for downstream audio LLM trainingInterruptible in-car or wearable voice UX

Frequently asked

How much does Kyutai Moshi cost to use?
Moshi is free and open source. Models are under CC-BY 4.0, code under MIT/Apache 2.0. You pay only for your own compute, requiring a 24GB+ GPU or Apple Silicon for self-hosting.
What hardware do I need to run Moshi?
You need a 24GB+ GPU for PyTorch inference or Apple Silicon for MLX. Weights are available in PyTorch, MLX, and Rust/Candle backends for production deployments.
Is Moshi better than traditional voice assistants?
Moshi processes audio natively without ASR/LLM/TTS pipelines, enabling interruptions and back-channels. It achieves roughly 200ms end-to-end latency on an L4 GPU, below human turn-taking thresholds.
Can I run Moshi on my Mac or iPhone?
Yes. MLX weights support int4/int8/bf16 inference for on-device Mac and iPhone. This allows prototyping voice interactions locally on Apple Silicon without external APIs.
What languages does Moshi support?
The documentation does not specify multilingual coverage. It is best for researchers and engineers needing self-hosted, low-latency spoken dialogue with open weights, rather than out-of-the-box multilingual support.
See alternatives to Kyutai Moshi →

Explore related

Reviews