Local TTS model

Higgs Audio v2

SOTA expressive TTS built on an LLM-audio backbone. Generates natural multi-speaker dialogue, spontaneous laughter, whispers and even background music. Beats ElevenLabs on MOS naturalness in several languages.

GPU recommended text-to-speech generation 8 languages Apache 2.0
Quality
9.7/10
Speed
7/10
Model size
5.5 GB
Voices
Zero-shot cloning + multi-speaker

Can Higgs Audio v2 run locally?

Higgs Audio v2 can generate speech locally for private voice workflows. Start with pip install higgs-audio.

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

emotiondialoguecloningstreamingmultilingual

Audio profile

Quality
9.7
Speed
7
Local
8.4

Best fit

Higgs Audio v2 is best for local voice cloning and expressive speech generation.

Hardware: gpuapple

Model details

Type
Local TTS model
Family
higgs
Latency
low
Formats
pytorchsafetensors
Languages
en, zh, fr, de, es, it, ja, ko
Context
LLM backbone with audio tokenizer, 3B params

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 higgs-audio

Good for

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

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