---
title: "Kyutai's Pocket TTS Now Speaks 6 Languages Faster Than Real-Time on CPU"
subtitle: "Kyutai's Pocket TTS adds French, Spanish, Portuguese, Italian, and German to its 100M-parameter model that runs faster than real-time on a laptop CPU with no GPU required."
url: "https://alphasignal.ai/news/kyutai-s-pocket-tts-now-speaks-6-languages-faster-than-real-time-on-cpu"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "kyutai"
company_url: "https://alphasignal.ai/company/kyutai_labs"
published: "2026-06-23T13:12:05.000Z"
updated: "2026-06-29T01:09:23.816Z"
type: "Repo"
topics:
  - "Audio"
  - "Open Source"
subtopics:
  - "Text To Speech"
  - "Voice Cloning"
upvotes: 39
source_url: "https://github.com/kyutai-labs/pocket-tts"
comments: 0
truncated: true
---

# Kyutai's Pocket TTS Now Speaks 6 Languages Faster Than Real-Time on CPU

> Kyutai's Pocket TTS adds French, Spanish, Portuguese, Italian, and German to its 100M-parameter model that runs faster than real-time on a laptop CPU with no GPU required.

[Pocket TTS](https://github.com/kyutai-labs/pocket-tts), the open-source text-to-speech model from French AI lab Kyutai, just went multilingual. The 100M-parameter model now speaks six languages, runs faster than real-time on a laptop CPU, and still fits in a single `pip install`. No GPU, no cloud API, no subscription.

## Six languages, same tiny footprint

Pocket TTS goes multilingual, with 100M-parameter models that can generate speech in six languages faster than real-time without a GPU, while also improving the quality of the English model while keeping the same size. The supported languages are:

* English
* French
* Spanish
* Portuguese
* Italian
* German

You can switch languages with a single flag. To generate German speech from the command line, for example:

```
uvx pocket-tts generate --language german --text "Hallo Welt, das ist ein Test."
```

The package supports Python 3.10 through 3.14, requires PyTorch 2.5+, and does not require the GPU version of PyTorch.

## The architecture behind the speed

Most TTS systems today work by first compressing audio into discrete tokens using a neural codec (think of it like lossy compression), then running a language model over those tokens. Audio tokens are lossy: unlike text tokens, you cannot perfectly reconstruct audio from them, and improving quality means increasing bitrate, which means more tokens and more computation.

Pocket TTS takes a different approach. CALM (Continuous Audio Language Models) instantiates a large Transformer backbone that produces a contextual embedding at every timestep, and this sequential information then conditions an MLP that generates the next continuous frame of an audio VAE through consistency modeling, achieving higher quality at lower computational cost than discrete counterparts.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [kyutai-labs/pocket-tts GitHub Repository](https://github.com/kyutai-labs/pocket-tts)
- [Continuous Audio Language Models (CALM) - arXiv](https://arxiv.org/html/2509.06926v3)
- [Kyutai TTS - Official Page](https://kyutai.org/tts/)
- [kyutai/pocket-tts - Hugging Face Model Card](https://huggingface.co/kyutai/pocket-tts)
- [How to Build a Local AI Voice Agent with Pocket TTS - GetStream](https://getstream.io/blog/pocket-tts-voice-agent/)