Sign in Submit site

Chatterbox

github.com/resemble-ai/chatterbox AI Voice & Audio Open-source projectOpen source

The Chatterbox project provides an open-source text-to-speech system for speech generation.

Visit Chatterbox 24 alternatives
github.com/resemble-ai/chatterbox
Chatterbox homepage screenshot

About Chatterbox

Chatterbox is an open-source text-to-speech (TTS) project from Resemble AI, published as a GitHub repository. It is a family of speech generation models, each suited to different needs. Chatterbox-Turbo is a 350M-parameter English model aimed at low-latency voice agents, and it also supports narration and creative work. Chatterbox-Nano is a 110M-parameter English model for on-device and CPU inference. Chatterbox Multilingual V3 is a 500M-parameter model that covers 23+ languages and supports cross-language voice cloning.

The repository includes example scripts for generation and voice conversion, along with Gradio apps for speech generation. The source lists model sizes, languages, and benchmark-style figures such as Nano running at 3x realtime on 8 CPU cores. A separate hosted TTS service is mentioned, but it is not part of the repository and its pricing is not stated.

Key features

  • Paralinguistic tags such as [laugh] and [cough] in Turbo and Nano
  • Multilingual model covering 23+ languages, with cross-language voice cloning
  • Six dedicated single-language finetunes for priority languages
  • Nano model designed for CPU inference, reported at 3x realtime on 8 cores
  • Example scripts and Gradio apps for speech generation and voice conversion
  • Creative controls including CFG and exaggeration tuning for zero-shot TTS
Best for: Developers and teams building speech applications, voice agents, or multilingual voice features who want open-source TTS models they can run themselves.
Good for
  • Open-source code and models available in a public repository
  • Turbo uses less compute and VRAM than earlier Chatterbox models
  • Multilingual V3 is described as improving speaker similarity and reducing hallucinations
Watch out for
  • Turbo and Nano are listed as English-only models
  • Multilingual V3 has 500M parameters, larger than Turbo (350M) and Nano (110M)

Chatterbox at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026
open sourcepythonmacos

Chatterbox alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Voice & Audio

Well-known listings from the same topic.

All 227
Google Illuminateilluminate.google.comAlteredaltered.aiELSA Speakelsaspeak.comKreadoAIkreadoai.comPodwisepodwise.aiAddsubtitleaddsubtitle.ai
Related topicsAI Business ToolsAI Image GeneratorsAI Infrastructure & MLOpsAI Agents & AutomationAI Data & AnalyticsAI Chatbots & AssistantsAI Writing ToolsAI Video Generators

Chatterbox FAQ

Which Chatterbox model supports multiple languages?
Chatterbox Multilingual V3 is the general-purpose multilingual model, listed as supporting 23+ languages. Six dedicated single-language finetunes are also available for priority languages.
Can Chatterbox run on a CPU?
Chatterbox-Nano targets on-device and CPU inference. The source reports it running 3x faster than realtime on 8 CPU cores.
Do the models support non-speech sounds like laughter?
Yes. Paralinguistic tags such as [laugh], [chuckle], and [cough] are native to the Turbo and Nano models.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing

Listing maintained by Chris McClure and the WebIndexly editors · Updated Oct 13, 2026 · How we rank