← 回總覽

Chatterbox:全新开源的 10 秒声音克隆工具

📅 2026-03-17 15:28 Nav Toor 人工智能 4 分鐘 3819 字 評分: 88
Chatterbox 语音克隆 开源 TTS Python
📌 一句话摘要 Chatterbox 是一款 100% 开源工具,能从 10 秒音频片段中克隆任何声音,支持 23 种语言,并可在单个 GPU 上运行。 📝 详细摘要 这条推文介绍了 Chatterbox,它是 ElevenLabs 等付费服务的一个重要开源替代方案。它拥有一个 3.5 亿参数模型,能够在 23 种语言中生成带有情感细微差别(如笑声、咳嗽声)的语音。这款工具非常易用,仅需单个 GPU 和简单的 `pip install` 安装,即可在 MIT 许可证下免费提供高质量的 TTS(文本转语音)和语音转换功能。 📊 文章信息 AI 评分:88 来源:Nav Toor(@heyn

Title: Chatterbox: New Open-Source 10-Second Voice Cloning Tool ...

URL Source: https://www.bestblogs.dev/status/2033807575221997721

Published Time: 2026-03-17 07:28:06

Markdown Content: Skip to main content ![Image 1: LogoBestBlogs](https://www.bestblogs.dev/ "BestBlogs.dev")Toggle navigation menu Toggle navigation menuArticlesPodcastsVideosTweetsSourcesNewsletters

⌘K

Change language Switch ThemeSign In

Narrow Mode

Chatterbox: New Open-Source 10-Second Voice Cloning Tool ========================================================

Chatterbox: New Open-Source 10-Second Voice Cloning Tool ======================================================== ![Image 2: Nav Toor](https://www.bestblogs.dev/en/tweets?sourceId=SOURCE_47fc9a7d) ### Nav Toor

@heynavtoor

🚨Someone just open sourced a tool that clones any voice from a 10-second audio clip.

It's called Chatterbox. Give it a short recording of anyone's voice and it will generate new speech in that exact voice. Any words you want.

23 languages. One pip install. Free.

Here's what makes this one different:

→ 350M parameter model. Runs on a single GPU.

→ You can make the cloned voice laugh, cough, chuckle, and sigh

→ Works in English, Japanese, Chinese, Hindi, Arabic, French, and 17 more

→ Built-in watermarking so generated audio can be detected

→ Voice conversion mode turns YOUR voice into someone else's in real-time

Five lines of Python and it's talking:

pip install chatterbox-tts

from chatterbox.tts_turbo import ChatterboxTurboTTS

model = ChatterboxTurboTTS.from_pretrained(device="cuda")

wav = model.generate("Hello world", audio_prompt_path="any_voice.wav")

That's it. That voice now says whatever you type.

21.9K GitHub stars. 2.9K forks. MIT License.

ElevenLabs charges $5 to $99/month for this. Chatterbox does it for free.

100% Open Source.Show More

!Image 3: Tweet image

Mar 17, 2026, 7:28 AM View on X

7 Replies

6 Retweets

27 Likes

2,324 Views N Nav Toor @heynavtoor

One Sentence Summary

Chatterbox is a 100% open-source tool that clones any voice from a 10-second clip, supporting 23 languages and running on a single GPU.

Summary

This tweet introduces Chatterbox, a significant open-source alternative to paid services like ElevenLabs. It features a 350M parameter model capable of generating speech with emotional nuances (laughing, coughing) across 23 languages. The tool is highly accessible, requiring only a single GPU and a simple 'pip install', making high-quality TTS and voice conversion available for free under the MIT License.

AI Score

88

Influence Score 20

Published At Today

Language

English

Tags

Chatterbox

Voice Cloning

Open Source

TTS

Python HomeArticlesPodcastsVideosTweets

Chatterbox: New Open-Source 10-Second Voice Cloning Tool ... ===============

查看原文 → 發佈: 2026-03-17 15:28:06 收錄: 2026-03-17 18:00:54

🤖 問 AI

針對這篇文章提問,AI 會根據文章內容回答。按 Ctrl+Enter 送出。