#5656th of 67 in VoiceFor voice, speech and music
emotivoice
Text-to-speech engine with emotion and style prompts, English and Chinese
- Stars
- 8.5k
- License
- Apache-2.0
- Last commit
- Sep 2026
- Language
- Python
8,356 on 3 Apr 20268,541 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
EmotiVoice synthesizes speech in English and Chinese from over 2000 voices, with emotion (happy, sad, angry, excited and others) controlled through text prompts. It ships a Streamlit demo page on port 8501, a batch inference script, and an OpenAI-compatible TTS API with speed control. Voice cloning on personal data is documented on the wiki.
Who it is for: Developers needing self-hosted emotional TTS in English or Chinese
Strengths
- Prompt-controlled emotion and style across 2000+ voices in English and Chinese
- OpenAI-compatible TTS API on port 8000, with speed tuning
- Batch scripting interface plus Streamlit web demo
- Voice cloning recipes for DataBaker and LJSpeech datasets
Weaknesses
- Only English and Chinese; Japanese and Korean are still under development
- Manual setup needs separate pretrained model downloads from ModelScope or Hugging Face
- Inference input uses a pipe-delimited phoneme format that needs a frontend step
- Docker quickstart requires an NVIDIA GPU and container toolkit; no release tags published
What it needs
- GPU required
- Docker
- Needs Docker, NVIDIA container toolkit, PyTorch, Streamlit, FastAPI, Git LFS
- Models: PromptTTS-based acoustic model with HiFi-GAN vocoder, SimBERT Chinese
- port 8501
Quick answers
Is emotivoice open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Can you run emotivoice with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does emotivoice need a GPU?
Yes, it needs a GPU.
Also in Voice
See all 67| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 97 out of 100 |
| 2 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 89 out of 100 |
| 3 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 89 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 82 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 81 out of 100 |