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

Bluetts

Bluetts is the public-facing name for BlueTTS, a Python library that synthesizes multilingual speech from text using ONNX Runtime. It provides an inference interface, model downloads and voice JSON configurations, and can return audio samples for writing to WAV files.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Bluetts — 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 BlueTTS when you need a documented Python workflow for generating speech from text with an ONNX model, selecting a voice JSON and saving the resulting audio.

Who it is for

  • Python developers adding speech synthesis to a software workflow.
  • People building voice-preview or batch text-to-speech tools that save audio files.

Documented uses

  • Generate speech audio from text in a supported language.
  • Select a supplied voice configuration for synthesis.
  • Process numbers, dates, prices and codes as spoken words.
  • Include inline language spans in text, such as English within Hebrew input.
Before you choose

Requirements & limits

The repository is public and identifies the project license as MIT.

  • The documented setup requires Python 3.12 or later and uv.
  • The current model bundle is downloaded separately from the repository.
  • Hebrew grapheme-to-phoneme processing uses RenikudPlus and downloads additional weights on first use.
  • The older supported ONNX bundle is identified as the only bundle containing the graphs used for zero-shot voice conversion.
  • OpenVINO, CUDA, voice export and TensorRT are described as optional, use-case-specific extras.

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 BlueTTS and synthesize a WAV file

Install the project, download its current ONNX model and save synthesized text as a WAV file.

Before you start

  • Python 3.12 or later
  • uv
  • A repository checkout and the downloaded ONNX model bundle
  • A voice JSON file from the repository's voices directory

Steps

  1. Clone the BlueTTS repository and change into its directory.

  2. Run the command below to install the project dependencies.

    Documented command
    uv sync

  3. Download notmax123/BlueTTS2.5-onnx into ./onnx_models using the documented Hugging Face CLI command.

  4. Initialize BlueTTS with the model directory and a voice JSON, synthesize text, then write the returned samples and sample rate to a WAV file with soundfile.

Expected outcome

A WAV file containing synthesized speech from the supplied text.

Guide limitations

  • The README specifies Python 3.12 or later and uv.
  • For Hebrew synthesis, RenikudPlus downloads its own weights the first time it is used.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
maxmelichov/BlueTTS · Official homepage title · retained in its source language
How we review sourcesSuggest a correction