Local TTS model

KorvaTTS

Q: Can KorvaTTS run locally?

KorvaTTS is listed by LocalClaw as a local TTS option. Hardware fit depends on runtime, model size and backend support.

Catalogue summary: Apache-licensed Vietnamese-first on-device TTS model for natural code-switching with embedded English. It is trained from scratch on Vietnamese speech, ships ONNX Runtime weights and 10 bundled voice styles, runs on CPU without an API call, and outputs 44.1 kHz WAV audio.

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

Edge readytext-to-speech generation2 languagesApache 2.0

Choose an app

Start with Recommended. No terminal commands are shown.

Compare speech models

Open model filesRecommended verified starting point Open in UnslothLaunches Unsloth Desktop on this model Open Python packageVerified package page without exposing a command Open on Hugging FaceFiles, licence and model card Check 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

8.6/10

Catalogue speed

9.2/10

Model size

99M params; ~0.40 GB ONNX assets

Voices

10 bundled Vietnamese voice styles; voice cloning is on the roadmap, not in this release

Can KorvaTTS run locally?

KorvaTTS 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.

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

Upstream source

multilinguallow-latencycontrollable

Audio profile

Cat. quality

8.6

Cat. speed

9.2

Audio

8.8

Best fit

KorvaTTS is best for fast on-device voice responses and local assistants.

Hardware: cpugpuappleedge

Model details

Type

Local TTS model

Family

korva

Latency

low

Formats

onnx

Languages

vi, en

Context

ONNX Runtime CPU path, optional onnxruntime-gpu for CUDA, Python CLI/package, browser-compatible Supertonic 3 graph signatures and 44.1 kHz output

Install locally

Check runtimeConfirm the backend supports onnx on your machine.

Open recommended setupUse the app and model links above. LocalClaw does not expose a terminal command.

Test locallyRun a short private audio prompt before moving into production workflows.

Good for

text-to-speech generation
Edge ready local workflows
multilingual, low-latency, controllable

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