Local TTS model

Pocket TTS

Q: Can Pocket TTS run locally?

Pocket TTS is listed by LocalClaw as a local TTS option. Hardware fit depends on runtime, model size and backend support.

Catalogue summary: Kyutai's CC-BY-4.0 lightweight local TTS model built for fast CPU speech generation without a cloud API. The official Hugging Face release ships downloadable safetensors weights, a Pocket-TTS Python package and CLI, audio streaming, voice prompts and a local HTTP server path; the model card lists 100M parameters, English support, roughly 200 ms first audio chunk latency and about 6x real-time CPU generation on a MacBook Air M4.

Repository editorial metadata; verify comparative claims in the linked upstream material.

Edge readytext-to-speech generation1 languagesCC-BY-4.0

Choose an app

Start with Recommended. No terminal commands are shown.

Compare speech models

Open model filesRecommended verified starting point Open in UnslothLaunches Unsloth Desktop on this model Open Python packageVerified package page without exposing a command Open on Hugging FaceFiles, licence and model card Check my machineOptional: verify the fit with your saved hardware

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Catalogue quality

8.8/10

Catalogue speed

9.6/10

Model size

100M params; ~0.24 GB safetensors

Voices

Bundled Kyutai voices plus local voice-prompt cloning from user-provided WAV/MP3 samples

Can Pocket TTS run locally?

Pocket TTS can generate speech locally for private voice workflows. Use the verified setup options on this page; no terminal command is required to choose the right path.

CC-BY-4.0 license. Review upstream restrictions before commercial use.

Upstream source

cloningstreamingrealtimelow-latency

Audio profile

Cat. quality

8.8

Cat. speed

9.6

Audio

9.1

Best fit

Pocket TTS is best for local voice cloning and expressive speech generation.

Hardware: cpuappleedge

Model details

Type

Local TTS model

Family

kyutai

Latency

ultra-low

Formats

pytorchsafetensors

Languages

Context

Official Pocket-TTS package and CLI, CPU PyTorch path, local serve command, audio streaming, no GPU requirement, and client-side/community ONNX, Candle, MLX and desktop app implementations noted by Kyutai

Install locally

Check runtimeConfirm the backend supports pytorch, safetensors on your machine.

Open recommended setupUse the app and model links above. LocalClaw does not expose a terminal command.

Test locallyRun a short private audio prompt before moving into production workflows.

Good for

text-to-speech generation
Edge ready local workflows
cloning, streaming, realtime

Watch before shipping

Validate pronunciation, latency and artifacts with your own voice samples.
Review the upstream license and acceptable-use notes.
Benchmark on your target CPU, Apple Silicon or GPU setup.

Related TTS and speech models

Samuel Vitorino / HALO Research Sopro V2 Turbo Local TTS model · Q 9.2 · Speed 9.4 Neuphonic NeuTTS Air Local TTS model · Q 9 · Speed 9.5 Fluxions AI Vui Nano Local TTS model · Q 8.9 · Speed 9.2 Nineninesix Gepard 1.0 Local TTS model · Q 8.9 · Speed 9.2 OpenMOSS / MOSI.AI MOSS-TTS-Nano Local TTS model · Q 8.5 · Speed 9.7 Kyutai Kyutai STT 2.6B English Local ASR model · Q 9.4 · Speed 9.5 hexgrad Kokoro TTS Local TTS model · Q 9.2 · Speed 9.8 Mistral AI Voxtral 4B TTS 2603 Local TTS model · Q 9.5 · Speed 9.1

CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw