# cosin2077/easyVoice

开源文本转语音工具，支持超长文本，多角色配音

Repository: https://github.com/cosin2077/easyVoice
Canonical: https://ross.abutalabs.com/products/easyvoice
Homepage: https://easyvoice.ioplus.tech
Language: TypeScript
License Family: other
Topics: edge-tts, tts, tts-engines
Last push: 2026-01-26T03:04:33+00:00

## Health v2 (maintenance only)
Score: 49/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 64, release rhythm 35, longevity 38
- inputs: {"age_days": 536, "days_push": 219, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2287, forks 374 (observed 2026-08-28T04:06:34.083183+00:00)

## What it is
EasyVoice is an open-source text-to-speech application that converts long texts and novels into high-quality audio with streaming playback and auto-generated subtitles. It supports multi-character voice acting, AI-recommended voice configurations, and can be self-hosted via Docker or Node.js.

## Use cases
- convert novels into audiobooks
- generate voiceover for videos with subtitles
- create multi-character audio dramas from text
- turn long Chinese or English text into speech
- self-host a free unlimited TTS service
- generate mp3 audio from scripts via API

## When to choose
- you need free TTS with no length or character limits
- you want multi-role voices for novels or stories
- you need streaming playback of very long texts
- you want a self-hosted TTS solution with a web UI and API

## When to avoid
- you need offline TTS without Edge TTS network dependency
- you need a license-guaranteed project (no license file)
- you need non-Edge neural voices or commercial TTS engines
- you need a simple CLI-only converter without a server

## Facets
- artifact type: application
- maturity: active
- function: tts, speech-recognition, http-server
- domain: speech-processing, self-hosted
- platform: self-hosted, cross-platform
- tags: edge-tts, audiobook-generation, subtitle-generation, multi-voice, streaming-audio, novel-to-speech, audio, natural-language-processing, nodejs, docker, web-server

## Member repositories
- cosin2077/easyVoice (main) score 49

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:34.083183+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 2026-08-30T02:40:51.658469+00:00, confidence not recorded.
  - readme: https://github.com/cosin2077/easyVoice (fetched 2026-08-28T04:06:34.083183+00:00, sha 92c4c037f210)
  - homepage: https://easyvoice.ioplus.tech (fetched 2026-08-29T10:21:27.729321+00:00, sha 279d577a606a)
- Data as of 2026-08-30T08:39:29.467469+00:00.