Pocket TTS

Spec sheet

What it does

Pocket TTS is a lightweight text-to-speech application designed to run efficiently on CPUs.Read 12 Oct 2026 · kyutai-labs.github.io

Purpose

Pocket TTS is a lightweight text-to-speech application designed to run efficiently on CPUs.Read 11 Oct 2026 · kyutai-labs.github.io

Platforms

windows,macos,linux,api,self_hostedRead 20 Sep 2026 · kyutai-labs.github.io

Free plan

YesRead 20 Sep 2026 · kyutai-labs.github.io

Integrations

The project lists community projects including a Wyoming protocol Docker container for Home Assistant Voice and a Unity 6 integration.Read 12 Oct 2026 · kyutai-labs.github.io

Support

The maker invites users to open issues or pull requests on GitHub and accepts contributions.Read 11 Oct 2026 · kyutai-labs.github.io

Headquarters

Paris, FranceRead 28 Sep 2026 · kyutai-labs.github.io

API access

YesRead 20 Sep 2026 · kyutai-labs.github.io

Browser availability

The maker offers a browser demo and says the model can run client-side in a browser, while noting that browser implementations are not officially supported.Read 11 Oct 2026 · kyutai-labs.github.io

Browser demo

The documentation links to a Kyutai website demo that can generate speech in the browser without installation.Read 12 Oct 2026 · kyutai-labs.github.io

Commercial use

YesRead 20 Sep 2026 · kyutai-labs.github.io

CPU performance

The project reports about six times real-time generation on a MacBook Air M4 CPU using two CPU cores.Read 12 Oct 2026 · kyutai-labs.github.io

Export formats

WAVRead 20 Sep 2026 · kyutai-labs.github.io

Interfaces

It offers a Python library, command-line interface, and local HTTP server with a web interface at localhost:8000.Read 12 Oct 2026 · kyutai-labs.github.io

Languages

6Read 20 Sep 2026 · kyutai-labs.github.io

Languages

The documented pretrained language models cover English, French, German, Portuguese, Italian, and Spanish.Read 12 Oct 2026 · kyutai-labs.github.io

License and access

The Hugging Face model card lists the model license as CC-BY-4.0 and says users must agree to share contact information to access the model files.Read 11 Oct 2026 · huggingface.co

Long inputs

Pocket TTS can handle infinitely long text inputs.Read 12 Oct 2026 · kyutai-labs.github.io

Long text

The model can handle infinitely long text inputs.Read 11 Oct 2026 · kyutai-labs.github.io

Model size

The model has 100 million parameters.Read 12 Oct 2026 · kyutai-labs.github.io

Platform setup

The maker documents installation on Linux, macOS, and Windows; on Linux, its default PyTorch installation may download several gigabytes of CUDA runtime wheels unless users choose the CPU-only index.Read 11 Oct 2026 · kyutai-labs.github.io

Requirements

The package supports Python 3.10 through 3.14 and requires PyTorch 2.5 or later.Read 11 Oct 2026 · github.com

Runtime requirements

The package supports Python 3.10 through 3.14 and requires PyTorch 2.5 or newer; it does not require the GPU version of PyTorch.Read 12 Oct 2026 · kyutai-labs.github.io

Security and use policy

The project prohibits voice impersonation or cloning without explicit and lawful consent, along with deceptive, harmful, or privacy-invasive uses.Read 12 Oct 2026 · kyutai-labs.github.io

Streaming and latency

It supports audio streaming and reports about 200 ms to produce the first audio chunk.Read 12 Oct 2026 · kyutai-labs.github.io

Support and contributions

The project invites users to open GitHub issues or pull requests and links to development instructions.Read 12 Oct 2026 · github.com

Unsupported feature

Adding silence in text input to generate pauses is currently unsupported.Read 12 Oct 2026 · kyutai-labs.github.io

Use restrictions

The maker prohibits voice impersonation or cloning without explicit lawful consent and other illegal, harmful, deceptive, or privacy-invasive uses.Read 11 Oct 2026 · kyutai-labs.github.io

Voice cloning

Voice cloning accepts a WAV file as the voice input, and the project provides an export command to save voice state for faster loading.Read 12 Oct 2026 · kyutai-labs.github.io

Plans and prices

Every Pocket TTS plan and price →

Where Specifiction places it

• Text-to-Speech Software#46 of 2238.6
• Text-to-speech tools#54 of 2338.6