OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Vieneu Tts

VieNeu-TTS is an Apache-2.0 Python project that synthesizes Vietnamese speech from text. Its repository includes the v3 Turbo SDK and a simplified web interface, with preset voices, short-clip voice cloning, CPU or CUDA inference, and a documented API-server option.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Vieneu Tts — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use VieNeu-TTS when you need a developer-oriented Vietnamese text-to-speech component and want to choose between local CPU and NVIDIA GPU inference. Its repository is also relevant for evaluating preset voices, short-clip cloning, conversation mode or a documented streaming API server.

Who it is for

  • Developers building Vietnamese narration or speech-generation workflows.
  • Teams exploring Vietnamese voice cloning from short audio references.
  • Application builders seeking an on-device or self-hosted speech synthesis component.

Documented uses

  • Convert Vietnamese scripts into audio using a preset voice.
  • Generate Vietnamese audio using a voice reference clip.
  • Add multi-speaker conversation-style synthesis to a script.
  • Run speech synthesis locally on CPU or use CUDA-based inference.
Before you choose

Requirements & limits

The repository is public and identifies the project as Apache-2.0 licensed. The README describes v3 Turbo as the latest open-source version; v4 is described as proprietary and available through the VieNeu API or vieneu.io.

  • The SDK defaults to v3 Turbo, which the repository describes as producing 48 kHz audio.
  • The minimal CPU path uses ONNX Runtime and does not require PyTorch; CUDA inference uses the PyTorch engine.
  • Voice cloning is described as using a 3–8 second clip; built-in preset voices do not require a reference clip.
  • The README labels emotion and non-verbal cues experimental.
  • The GitHub web interface is a simplified demo; the repository assigns dubbing, lecture and short-video features to the separate official app.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the local web interface

Install the repository dependencies and start the VieNeu-TTS web UI.

Before you start

  • Python project environment managed with uv.
  • For CPU and macOS, use the minimal dependency path; the repository also documents a CUDA extra for GPU use.

Steps

  1. Install uv using the command for your operating system in the repository README.

  2. Clone https://github.com/pnnbao97/VieNeu-TTS.git and change into the VieNeu-TTS directory.

  3. Run the command below for CPU/macOS, or the command below for the documented GPU path.

    Documented command
    uv sync
    Documented command
    uv sync --extra cuda

  4. Run the command below and open http://127.0.0.1:7860.

    Documented command
    uv run vieneu-web

Expected outcome

The local VieNeu-TTS web interface is available at the documented loopback address.

Guide limitations

  • These steps cover setup and starting the web UI; they do not establish compatibility with a particular machine.
  • The repository describes the GitHub interface as a simplified demo, separate from the official app's dubbing, lecture and short-video features.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
pnnbao97/VieNeu-TTS · Official homepage title · retained in its source language
How we review sourcesSuggest a correction