LocalClaw/TTS/Step-Audio 2 Mini
Local TTS model

Step-Audio 2 Mini

Open-source multi-modal speech LLM. Unified understanding + generation in one model - ASR, TTS, voice conversion, speech dialogue. Strong expressive control and paralinguistic features. Available in Mini (8B) and Full variants.

GPU recommended text-to-speech generation 3 languages Apache 2.0
Compare TTS models Open source page
Quality
9.3/10
Speed
7.5/10
Model size
4.8 GB
Voices
Multi-speaker + voice conversion

Can Step-Audio 2 Mini run locally?

Step-Audio 2 Mini can generate speech locally for private voice workflows. Start with pip install step-audio.

Apache 2.0 license. Still verify upstream usage notes before shipping.

pip install step-audio Upstream source
cloningdialogueemotionstreamingmultilingual

Audio profile

Quality
9.3
Speed
7.5
Local
8.5

Best fit

Step-Audio 2 Mini is best for local voice cloning and expressive speech generation.

Hardware: gpuapple

Model details

Type
Local TTS model
Family
step
Latency
low
Formats
pytorchsafetensors
Languages
en, zh, ja
Context
Unified speech LLM (ASR + TTS + dialogue)

Install locally

01
Check runtimeConfirm the backend supports pytorch, safetensors on your machine.
02
Install modelUse the upstream command or repository instructions.
03
Test locallyRun a short private audio prompt before moving into production workflows.
pip install step-audio

Good for

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

Boson AI Higgs Audio v2 Local TTS model · Q 9.7 · Speed 7 Alibaba FunAudioLLM CosyVoice 2 Local TTS model · Q 9.3 · Speed 8.8 OpenBMB VoxCPM2 Local TTS model · Q 9.4 · Speed 8.3 Nari Labs Dia Local TTS model · Q 9.3 · Speed 7 Microsoft Research VibeVoice 1.5B Local TTS model · Q 9.4 · Speed 6.5 Speech Research (SWivid) F5-TTS v1.1 Local TTS model · Q 9.5 · Speed 9.2 Alibaba Cloud (Qwen Team) Qwen3 TTS Local TTS model · Q 9.5 · Speed 8.5 Zyphra Zonos v0.1 Local TTS model · Q 9.5 · Speed 8.5
CompareBrowse all TTS models Local AIBrowse LLM models macOS appGet LocalClaw