Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

VieNeu-TTS

VieNeu-TTS: An on-device Vietnamese text-to-speech system with instant voice cloning.

What problem it solves

Developers need Vietnamese speech synthesis that can run locally, produce natural reading styles, and support voice cloning without sending audio to a hosted service. They also need integration paths for SDK use, streaming applications, and an OpenAI-compatible API.

Key features

  • Instant voice cloning — Clone a voice from a short reference recording. The clipping pipeline automatically denoises and trims reference audio before extracting its speaker profile.

    Source: README

  • Built-in Vietnamese voices — The engine includes preset voices representing Northern, Central, and Southern Vietnamese regions, with different genders and speaking characters. Voices can also be registered and reused by name.

    Source: README

  • Streaming and batched synthesis — Generate complete speech, process multiple texts as a batch, or iterate over streamed audio chunks. A continuous-batching scheduler is available for concurrent GPU streams.

    Source: README, examples

  • SDK and API integration — Use the Python SDK directly or serve speech through an OpenAI-compatible endpoint. The server supports PCM or WAV responses delivered as chunked bodies or SSE.

    Source: README, apps/openai_speech.py

  • Local CPU and GPU execution — The core installation supports CPU inference through ONNX Runtime without importing PyTorch, while CUDA systems can automatically use the PyTorch engine through the same API.

    Source: README

Quick start

Copied verbatim from the project's README.

pip install vieneu

Who it may suit

This project may suit developers building Vietnamese speech applications, voice assistants, dubbing workflows, or local TTS tools. It may also suit researchers experimenting with voice cloning, streaming synthesis, and LoRA fine-tuning.

Topics to discuss

  • Which applications would benefit most from local Vietnamese voice cloning?

  • How should users balance audio fidelity and speed across CPU, GPU, Turbo, and Nano modes?

  • What community examples or integrations would be most useful for the OpenAI-compatible API?


Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/pnnbao97/VieNeu-TTS#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/pnnbao97/VieNeu-TTS

Comments

…