Local TTS model

ZONOS2

Q: Can ZONOS2 run locally?

ZONOS2 is listed by LocalClaw as a local TTS option. Hardware fit depends on runtime, model size and backend support.

Catalogue summary: Zyphra's second-generation open-weight multilingual TTS MoE with high-fidelity voice cloning, streaming server output, offline Python inference and emotion controls. The canonical HF checkpoint ships a 15.3GB model file and the official runtime targets local Linux CUDA through Mini-SGLang, with a separate ggml path noted for CPU and cross-platform support.

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

GPU recommendedtext-to-speech generation34 languagesMIT / Apache-2.0 metadata

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 official projectApplication source and guided setup 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

9.6/10

Catalogue speed

8.5/10

Model size

15.4 GB HF repo; Linux CUDA recommended

Voices

Reference-audio voice cloning plus speaker embeddings

Can ZONOS2 run locally?

ZONOS2 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.

MIT / Apache-2.0 metadata license. Still verify upstream usage notes before shipping.

Upstream source

cloningstreamingrealtimemultilingualemotioncontrollable

Audio profile

Cat. quality

9.6

Cat. speed

8.5

Audio

9.2

Best fit

ZONOS2 is best for local voice cloning and expressive speech generation.

Hardware: gpucpu

Model details

Type

Local TTS model

Family

zonos

Latency

low

Formats

pytorchggml

Languages

en, zh, ja, ko, ru, it, pt, fr, es, vi, de, he, nl, sv, hi, ta, te, th, no, bn, tl, ar, da, id, pl, uk, ro, fi, hu, lt, et, sk, hr, lv

Context

MoE TTS, 15.3GB model.pth, Mini-SGLang streaming server, offline Python API, emotion sliders and OpenAI-compatible local endpoint

Install locally

Check runtimeConfirm the backend supports pytorch, ggml 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
GPU recommended 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

CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw