TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Ask HN: Open-source, local Text-to-Speech (TTS) generators

1 点作者 dv35z大约 1 年前
Hola amigos - I just noticed that https:&#x2F;&#x2F;coqui.ai&#x2F; is &quot;Shutting down&quot;.<p>I&#x27;m building a web app (React &#x2F; Django) which takes a list of affirmations &amp; goals (in Markdown files), puts them into a database (SQlite), and uses voice synthesis to create voice audio files of the phrases. These are combined with a relaxed backing track (ffmpeg), made into playlists of 10-20 phrases (randomly sampled, or according to a theme: &quot;mind&quot; &quot;body&quot; &quot;soul&quot;) and then play automatically in the morning &amp; evening (cron). This allows you to persistently hear &amp; vocalize your own goals &amp; good vibes over time.<p>I had been planning to use Coqui TTS as the local text-to-speech engine, but with this cancellation, I&#x27;d love to hear from the community what is a great open-source, local text-to-speech engine?<p>Generally, I learn both the highest quality commercially available technology (example: ElevenLabs), and also the best open-source equivalent. Would love to hear suggestions &amp; perspectives on this. What voice synth tools are you investing your time into learning &amp; building with?

2 条评论

illuminant大约 1 年前
Mozilla&#x27;s browser tts is kind of not bad, just parse and buffer one sentence at a time and it does all right.<p>For the backend, I&#x27;ve experimented with piper, which has a lot of voices and accents, though it&#x27;s tricky to buffer and sync long texts.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;rhasspy&#x2F;piper">https:&#x2F;&#x2F;github.com&#x2F;rhasspy&#x2F;piper</a>
082349872349872大约 1 年前
eSpeak NG?
评论 #40288818 未加载