netease-youdao/EmotiVoice
EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine
Combines prompt-based style control with acoustic modeling to synthesize speech with fine-grained emotion and prosody adjustment across 2000+ voices in English and Chinese. Built on PyTorch with a frontend processing pipeline (G2P, phoneme extraction) feeding into an acoustic model and neural vocoder, exposing both Streamlit web UI and OpenAI-compatible REST API for inference and batch processing. Supports voice cloning through fine-tuning on custom datasets via provided recipes (DataBaker, LJSpeech).
8,455 stars and 107 monthly downloads. No commits in the last 6 months. Available on PyPI.
Stars
8,455
Forks
746
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 13, 2024
Monthly downloads
107
Commits (30d)
0
Dependencies
18
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/netease-youdao/EmotiVoice"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
yeyupiaoling/MASR
Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。
coqui-ai/TTS
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
shivammehta25/Matcha-TTS
[ICASSP 2024] 🍵 Matcha-TTS: A fast TTS architecture with conditional flow matching
gabrielmittag/NISQA
NISQA - Non-Intrusive Speech Quality and TTS Naturalness Assessment
DigitalPhonetics/IMS-Toucan
Controllable and fast Text-to-Speech for over 7000 languages!