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

Emotivoice

EmotiVoice is an open-source text-to-speech engine that synthesizes English and Chinese speech using multiple voices and emotion or style prompts. It includes web and scripting interfaces, and the repository documents self-hosted inference workflows.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Emotivoice — 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 EmotiVoice when you need English- or Chinese-language text-to-speech and want voice selection or prompt-based emotional expression; choose the local setup when you need its documented interactive or scripting workflows.

Who it is for

  • Audio and video creators making expressive voiceovers
  • Teams producing spoken English or Chinese content
  • Developers exploring batch or multi-speaker speech synthesis

Documented uses

  • Turn written English or Chinese text into speech.
  • Create speech with a selected voice and emotional style.
  • Generate batches of speech through a scripting workflow.
  • Explore multi-speaker dialogue or character speech.
Before you choose

Requirements & limits

The repository identifies EmotiVoice as open source under the Apache-2.0 license.

  • Self-hosted Docker use requires a machine with an NVIDIA GPU and NVIDIA Container Toolkit, according to the README.
  • The documented full installation uses Python 3.8, PyTorch, torchaudio and additional dependencies.
  • The inference workflow depends on pretrained models and a structured input format containing speaker, style or emotion prompt, phonemes and content.
  • English and Chinese are documented; Japanese and Korean are listed as future work.
  • The README says style control uses pitch, speed, energy and emotion, and does not use gender.

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 EmotiVoice’s local interactive demo

Install the documented dependencies and launch the project’s interactive TTS demo page.

Before you start

  • Python 3.8 in a Conda environment
  • PyTorch and torchaudio, plus the listed Python dependencies
  • Pretrained model files
  • Streamlit

Steps

  1. Create and activate a Conda environment using Python 3.8.

  2. Install torch and torchaudio, the listed project dependencies, and the NLTK averaged_perceptron_tagger_eng resource.

  3. Download the pretrained model files as described in the README’s model and inference sections.

  4. Install Streamlit and run streamlit run demo_page.py.

Expected outcome

The README’s interactive TTS demo page is launched locally.

Guide limitations

  • This covers setup and launching the demo, not a verified synthesis result.
  • The README directs users to its pretrained-model instructions if model downloads cause issues.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
netease-youdao/EmotiVoice · Official homepage title · retained in its source language
How we review sourcesSuggest a correction