LocalClaw/TTS/AuK
Local TTS model

AuK

Catalogue summary: 1.5B MIT-licensed foundation model for local speech generation and editing. AuK supports zero-shot TTS, instruction-based TTS, speech content editing, acoustic and paralinguistic editing, speech enhancement, speech separation and target-speaker extraction through one natural-language instruction interface.

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

GPU recommendedtext-to-speech generation2 languagesMIT
Choose an app

Start with Recommended. No terminal commands are shown.

Compare speech models
Open model filesRecommended verified starting pointOpen in UnslothLaunches Unsloth Desktop on this modelOpen official projectApplication source and guided setupOpen on Hugging FaceFiles, licence and model cardCheck 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
9.3/10
Catalogue speed
7.2/10
Model size
6.12GB AuK base safetensors plus 637MB VAE; requires Qwen2.5-Omni-3B encoder weights
Voices
Zero-shot TTS, voice-description TTS and instruction-guided speech editing

Can AuK run locally?

AuK 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 license. Still verify upstream usage notes before shipping.

Upstream source
cloningcontrollableemotion

Audio profile

Cat. quality
9.3
Cat. speed
7.2
Audio
8.6

Best fit

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

Hardware: gpu

Model details

Type
Local TTS model
Family
auk
Latency
medium
Formats
pytorchsafetensorssglang
Languages
en, zh
Context
1.5B speech generation/editing model; official docs show English and Chinese demos but do not publish a fixed language table; AuK-Flash supports 4-step inference; local CLI, Gradio, ComfyUI and SGLang-Omni paths

Install locally

01
Check runtimeConfirm the backend supports pytorch, safetensors, sglang on your machine.
02
Open recommended setupUse the app and model links above. LocalClaw does not expose a terminal command.
03
Test locallyRun a short private audio prompt before moving into production workflows.

Good for

  • text-to-speech generation
  • GPU recommended local workflows
  • cloning, controllable, emotion

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

Zyphra ZONOS2 Local TTS model · Q 9.6 · Speed 8.5 BreezeBlue Breeze TTS 2 Local TTS model · Q 9.6 · Speed 8.4 Zyphra Zonos v0.1 Local TTS model · Q 9.5 · Speed 8.5 Bilibili IndexTTS 2.5 Local TTS model · Q 9.5 · Speed 8.4 Boson AI Higgs TTS 3 4B Local TTS model · Q 9.7 · Speed 8 OpenBMB VoxCPM2 Local TTS model · Q 9.4 · Speed 8.3 NetEase Youdao Confucius4-TTS Local TTS model · Q 9.4 · Speed 8.2 Bilibili IndexTTS 2 Local TTS model · Q 9.4 · Speed 8
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw