Local TTS model

Coqui TTS (XTTS v2)

The most popular open TTS with incredible voice cloning from just 6 seconds of audio. Discontinued but widely used.

Apple Silicon ready text-to-speech generation 17 languages CPML (custom)
Quality
9.2/10
Speed
6/10
Model size
1.8 GB
Voices
Unlimited via cloning

Can Coqui TTS (XTTS v2) run locally?

Coqui TTS (XTTS v2) can generate speech locally for private voice workflows. Start with pip install TTS.

CPML (custom) license. Review upstream restrictions before commercial use.

cloningmultilingual

Audio profile

Quality
9.2
Speed
6
Local
8.2

Best fit

Coqui TTS (XTTS v2) is best for local voice cloning and expressive speech generation.

Hardware: gpuapple

Model details

Type
Local TTS model
Family
coqui
Latency
medium
Formats
pytorchonnx
Languages
en, es, fr, de, it, pt, pl, tr, ru, nl, cs, ar, zh, ja, hu, ko
Context
6s cloning, emotion

Install locally

01
Check runtimeConfirm the backend supports pytorch, onnx 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 TTS

Good for

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