# netease-youdao/EmotiVoice

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

Repository: https://github.com/netease-youdao/EmotiVoice
Canonical: https://ross.abutalabs.com/products/emotivoice
Language: Python
License: Apache-2.0
License Family: permissive
Topics: pytorch, speech, speech-synthesis, tts, multi-speaker, text-to-speech, deep-learning, prompt, emotivoice, ai, python, emotion, style
Last push: 2024-08-13T10:23:52+00:00

## Health v2 (maintenance only)
Score: 17/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 73
- inputs: {"age_days": 1029, "days_push": 750, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8523, forks 757 (observed 2026-08-28T04:10:23.331485+00:00)

## What it is
EmotiVoice is an open-source text-to-speech engine supporting English and Chinese with over 2000 voices and prompt-controlled emotional synthesis. It offers a web UI, scripting interface, HTTP API, and voice cloning with personal data.

## Use cases
- generate emotional speech from text
- convert text to speech in Chinese and English
- clone a custom voice from my own recordings
- batch generate voiceover audio via script
- run a self-hosted TTS API server
- create speech with different voices and emotions

## When to choose
- you need expressive, emotion-controlled TTS in English or Chinese
- you want many built-in voices plus voice cloning on your own data
- you prefer a self-hosted, Apache-2.0 licensed TTS engine with an API

## When to avoid
- you need languages beyond English and Chinese
- you need a lightweight TTS without GPU or deep-learning dependencies
- you need production-grade real-time streaming synthesis

## Facets
- artifact type: library
- maturity: active
- function: tts, speech-recognition, machine-learning, deep-learning, http-server, cli
- domain: speech-processing, artificial-intelligence, deep-learning
- platform: python
- tags: text-to-speech, voice-cloning, emotional-synthesis, multi-speaker, chinese-english, openai-compatible-api, pytorch, natural-language-processing, macos, linux, docker, gpu

## Member repositories
- netease-youdao/EmotiVoice (main) score 17

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:23.331485+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:26:40.406899+00:00, confidence not recorded.
  - readme: https://github.com/netease-youdao/EmotiVoice (fetched 2026-08-28T04:10:23.331485+00:00, sha 534a83bc8f39)
  - registry_pypi: https://pypi.org/pypi/emotivoice/json (fetched 2026-08-29T08:26:41.082164+00:00, sha a22facdeeadb)
- Data as of 2026-08-30T08:39:29.467469+00:00.