Local TTS model

Higgs TTS 3 4B

Q: Can Higgs TTS 3 4B run locally?

Higgs TTS 3 4B is listed by LocalClaw as a local TTS option. Hardware fit depends on runtime, model size and backend support.

Catalogue summary: Boson AI's newer conversational TTS checkpoint for local voice agents. It supports multilingual expressive speech, zero-shot voice cloning, inline emotion, style, prosody and sound-effect control, plus local serving through SGLang-Omni or vLLM-Omni.

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

GPU recommendedtext-to-speech generation102 languagesBoson Higgs TTS 3 Research and Non-Commercial License

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 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

9.7/10

Catalogue speed

8/10

Model size

9.32 GB

Voices

Zero-shot voice cloning from reference audio and transcript

Can Higgs TTS 3 4B run locally?

Higgs TTS 3 4B 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.

Boson Higgs TTS 3 Research and Non-Commercial License license. Review upstream restrictions before commercial use.

Upstream source

cloningstreamingmultilingualemotioncontrollabledialogue

Audio profile

Cat. quality

9.7

Cat. speed

Audio

9.2

Best fit

Higgs TTS 3 4B is best for local voice cloning and expressive speech generation.

Hardware: gpu

Model details

Type

Local TTS model

Family

higgs

Latency

low

Formats

transformerssafetensorsvllmsglang

Languages

multilingual

Context

4.65B BF16 params, 9.32GB safetensors storage, 24 kHz output, 8,192 token context

Install locally

Check runtimeConfirm the backend supports transformers, safetensors, vllm, sglang 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, multilingual

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