AivisSpeech: Generating Emotionally Rich Japanese Speech Synthesis Software

General Introduction

AivisSpeech is a Japanese speech synthesizer based on the VOICEVOX editor UI, which integrates the AivisSpeech Engine to easily generate emotionally rich speech. AivisSpeech integrates the AivisSpeech Engine, which makes it easy to generate emotionally rich speech.AivisSpeech supports a wide range of sound synthesis models, allowing users to generate high-quality Japanese speech with simple operations. Available for Windows and macOS, and especially recommended for Macs powered by the Apple Silicon, AivisSpeech's goal is to make advanced speech synthesis technology easily accessible to everyone for storytelling, news broadcasting, and more.

Function List

• Generate emotionally rich Japanese speech
• Supports a variety of sound synthesis models
• Easy-to-use user interface
• Compatible with Windows and macOS systems
• Support for AIVMX-formatted acoustic synthesis models
• Provides detailed documentation and FAQs for use

Using Help

Installation process

1. Visit AivisSpeech's GitHub page to download the latest version of the installer.
2. Select the corresponding installation package according to the operating system (Windows or macOS).
3. Run the installation program and follow the prompts to complete the installation.

Usage Process

1. Open the AivisSpeech software and go to the main screen.
2. In the "Settings" menu, select "Sound Synthesizer Module Management" to add a sound synthesizer model.
3. Select the desired sound synthesis model and click the "Append" button.
4. Enter the text to be synthesized in the main interface and select the appropriate emotion and voice style.
5. Click the "Generate" button and wait for the speech synthesis to complete.
6. After the synthesis is complete, you can play, save or export the generated speech file.

Detailed Functions

• Generate emotionally rich Japanese speech: By selecting different emotions and voice styles, users can generate a voice that meets specific emotional needs.
• Supports a variety of sound synthesis modelsAivisSpeech supports AIVMX-format sound synthesis models, allowing users to add and manage different models as needed.
• Easy-to-use user interfaceThe interface of the software is designed to be simple and intuitive, so users can easily get started with the operation.
• Compatible with Windows and macOS systemsAivisSpeech is easy to install and use for both Windows and macOS users.
• Provides detailed documentation and FAQs for use: Users can find detailed instructions and answers to frequently asked questions in the official documentation to help quickly solve problems in use.

common problems

1. How do I add a new sound synthesis model?
   • In the "Settings" menu, select "Sound Synthesizer Module Management", click the "Append" button, and select the model file you want to add.
2. What operating systems does the software support?
   • AivisSpeech supports Windows 10, Windows 11 and macOS 13 Ventura and above.
3. What formats can the generated voice files be exported to?
   • The generated voice files can be exported to WAV format for easy subsequent editing and use.
4. How do I solve problems encountered during installation?
   • See the installation guide and FAQ in the official documentation, or submit an issue on the GitHub page for help.