稳定信号免费/含内购低风险权限组合

Supertonic Text-to-Speech Voices

AI text-to-speech voices by Supertonic, synthesized locally in your browser

用户数2K当前公开安装规模

评分4.6商店平均评分

评论数7公开评论体量

Manifest 版本V3插件平台版本

7日增长0近 7 天净增用户

7日增长率0%相对周增长速度

视觉预览

Supertonic Text-to-Speech Voices 媒体预览

1 项素材

趋势

用户增长趋势

按已采集快照查看用户数变化。

用户增长趋势

评分趋势

近 7 日评分趋势

展示最近 7 日窗口内已采集的评分快照，辅助判断近期评分是否稳定。

7 日评分变化

起始值

4.57

日/周/月增长表现

同口径展示 1 天、7 天、30 天的绝对增长与增长率。

1日增长暂无数据

----

7日增长持平

00%

30日增长暂无数据

----

技术摘要

版本、语言与抓取信息

查看发布时间、版本、支持语言、最近更新和抓取时间。

版本2.0.0

ManifestV3

大小234MiB

语言数1English

发布时间--

插件简介

查看插件说明、主要功能和适用场景。

Supertonic is a collection of high-quality AI-powered text-to-speech (TTS) voices developed by Supertone, Inc. These voices are synthesized in-browser, requiring no cloud subscriptions, and are entirely free to use.

Once installed the voices will be added to the browser's list of available TTS voices, and usable by websites, apps, and by other browser extensions to synthesize text to audio.

Please be patient while Chrome downloads and installs this extension, as it is quite large due to the AI model being included in the distribution package.

Supertonic project page:

https://github.com/supertone-inc/supertonic

https://huggingface.co/Supertone/supertonic

评价

最新评论快照

查看最近评论和评分分布。

商店综合星级4.6Chrome 商店给出的聚合评分，包含只有打分但没有同步评论正文的情况

已同步评论均分4.3仅基于下方已同步评论正文计算

有内容评论4已同步的评论正文数量

总评分/评论数7Chrome 商店公开评分/评论计数

商店综合星级：4.6。下方星级分布只统计已同步评论正文；如果某个插件只有公开分数、没有真实评论正文，这里可能为空。

5★

4★

3★

2★

1★

Riaz Ali2026年2月24日

love the idea behind this, but for some reason my voices have trouble reading a paragraph like this: "If you tell me which ending you got (and which parts are confusing: Old Monkey, headband, stone, Erlang, etc.), I can break down those specific scenes beat‑by‑beat."

Antonie Nowak2026年1月18日

i would love if you added voices in polish

Reşit2026年1月4日

pls add turkish voices

Zane Billings2025年12月18日

This extension offers the best free text-to-speech voices I've found. The quality of these voices is on par with paid options like Speechify or Eleven Labs, and they are built upon open-source models readily accessible through platforms like Hugging Face and GitHub. It's my observation that high-quality text-to-speech voices often emerge from companies that also operate voice assistants. This is because these companies continuously gather and utilize vast amounts of voice data to refine and improve their models. This data-driven approach, in my opinion, is a key factor, and it might explain why Apple seems to be struggling with Siri; they haven't been as actively collecting and leveraging user data for AI development over the past decade in the same way.