TTS ONNX

Linux-first offline text-to-speech powered by Sherpa-ONNX.

TTS GPL-3.0 Linux First

Why TTS ONNX?

High-quality offline text-to-speech options for Korean, Chinese, and Japanese on Linux are still limited. TTS ONNX focuses on local, fast synthesis with practical multilingual workflows.

$ tts --lang en "Hello world" [OK] model: kitten-nano-en-v0_1-fp16 [OK] wrote: ./out.wav $ tts --service --config ./config/config.sherpa.yaml

What It Is

💻

Offline by design

Generate speech locally without requiring cloud inference.

📦

Model lifecycle tools

Install, list, and manage Korean, Chinese, Japanese, and English model packages.

🔄

Two runtime styles

Use one binary for command-line synthesis or service APIs.

TTS ONNX is a Linux-first text-to-speech runtime based on Sherpa-ONNX. It supports local/offline synthesis, multilingual voice workflows, direct CLI usage, and HTTP service mode.

Sherpa-ONNX Project URLs

How To Use It In CLI

Install models

tts --install-remote-id vits-mimic3-ko_KO-kss_low
tts --lang zh --install-remote-id vits-piper-zh_CN-huayan-medium
tts --lang ja --install-remote-id kokoro-int8-multi-lang-v1_0
tts --install-remote-id kitten-nano-en-v0_1-fp16

Synthesize speech

tts --lang ko "안녕하세요. 오프라인 테스트입니다."
tts --lang zh "这是中文语音合成测试。"
tts --lang ja "こんにちは。オフラインテストです。"
tts --lang en "Hello, this is an offline test."
tts --out ./out.wav "save this audio"

How To Use It As A Service

tts --service --config ./config/config.sherpa.yaml
bash ./scripts/install-user-unit.sh
bash ./scripts/enable-user-service.sh
curl -fsS http://127.0.0.1:18741/v1/health
curl -X POST http://127.0.0.1:18741/v1/speak \
  -H 'content-type: application/json' \
  -d '{"text":"hello world","lang":"en","format":"wav"}' \
  --output out.wav

Base service URL: http://127.0.0.1:18741/v1 | Endpoints: /health, /models, /models/install, /speak, /stop, /metrics

Download & Source

GitHub Download Releases ❤ Support Open Source