emotivoice

We have hosted the application emotivoice in order to run this application in our online workstations with Wine or directly.

Quick description about emotivoice:

EmotiVoice is a multi-voice, prompt-controlled text-to-speech engine designed to generate highly expressive speech across thousands of voices. It supports both English and Chinese and ships with over 2,000 preset voices, making it suitable for everything from characters and virtual anchors to narration and dialogue. The core idea is prompt-based emotional and style control: you can ask the engine to speak “happy,” “sad,” “excited,” or with other high-level style prompts that shape prosody, pitch, speed, and energy. EmotiVoice provides multiple ways to interact with it, including a web interface, a Docker image, an HTTP API (including an OpenAI-compatible TTS API), and Python scripts for batch synthesis. It also supports voice cloning with your own data, backed by recipes for popular datasets like DataBaker and LJSpeech, so you can train or adapt voices to custom personas.

Features:

• Multi-voice TTS engine with over 2,000 English and Chinese voices
• Prompt-controlled emotional synthesis (happy, excited, sad, angry and more)
• Web UI, Docker image, and OpenAI-compatible HTTP TTS API for easy access
• Support for voice cloning using your own recordings and provided training recipes
• Batch synthesis and phoneme-based workflows via Python scripts and frontend tools
• Apache-licensed project powered by modern TTS components and an active roadmap

Programming Language: Python.
Categories: