Local TTS model

Dia

1.6B dialogue TTS - generates realistic two-speaker conversations from a single transcript. Supports non-verbal cues like [laughs], [coughs], [sighs] natively.

Apple Silicon ready text-to-speech generation 1 languages Apache 2.0
Quality
9.3/10
Speed
7/10
Model size
3 GB
Voices
2-speaker dialogue + voice cloning

Can Dia run locally?

Dia can generate speech locally for private voice workflows. Start with pip install dia-tts.

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

dialogueemotioncloningstreaming

Audio profile

Quality
9.3
Speed
7
Local
8.4

Best fit

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

Hardware: gpuapple

Model details

Type
Local TTS model
Family
dia
Latency
medium
Formats
pytorch
Languages
en
Context
Non-verbal: [laughs] [coughs] [sighs]

Install locally

01
Check runtimeConfirm the backend supports pytorch 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 dia-tts

Good for

  • text-to-speech generation
  • Apple Silicon ready local workflows
  • dialogue, emotion, 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