# resemble-ai/chatterbox

SoTA open-source TTS

Repository: https://github.com/resemble-ai/chatterbox
Canonical: https://ross.abutalabs.com/products/chatterbox
Homepage: https://resemble-ai.github.io/chatterbox_demopage/
Language: Python
License: MIT
License Family: permissive
Last push: 2026-07-21T12:27:05+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 8, longevity 35
- inputs: {"age_days": 497, "days_push": 43, "days_rel": 446, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 26163, forks 3518 (observed 2026-08-28T04:11:38.840534+00:00)

## What it is
Chatterbox is a family of state-of-the-art open-source text-to-speech models by Resemble AI, including multilingual and low-latency Turbo variants with zero-shot voice cloning. It is MIT-licensed and supports emotion exaggeration control and paralinguistic tags like [laugh] and [cough].

## Use cases
- generate speech from text with a cloned voice
- build a voice agent with low-latency TTS
- create voiceovers for videos and memes
- clone a voice across multiple languages
- add laughs and coughs to synthesized speech
- run an open-source alternative to ElevenLabs

## When to choose
- you need high-quality open-source TTS with voice cloning under a permissive MIT license
- you want multilingual speech generation or emotion/exaggeration control
- you need low-latency speech for AI agents and have a GPU

## When to avoid
- you need a fully managed hosted TTS API without managing model inference
- you have no GPU and need real-time generation
- you need languages outside the model's supported coverage

## Facets
- artifact type: library
- maturity: active
- function: tts, speech-recognition, machine-learning, llm-inference
- domain: speech-processing, artificial-intelligence, deep-learning
- platform: python, cross-platform
- tags: voice-cloning, zero-shot-tts, multilingual, emotion-control, paralinguistic-tags, open-weights, audio, gpu

## Member repositories
- resemble-ai/chatterbox (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:38.840534+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 2026-08-29T16:55:55.713460+00:00, confidence not recorded.
  - readme: https://github.com/resemble-ai/chatterbox (fetched 2026-08-28T04:11:38.840534+00:00, sha 216ad51a586f)
  - homepage: https://resemble-ai.github.io/chatterbox_demopage/ (fetched 2026-08-29T07:52:20.184685+00:00, sha eff1ca7d1398)
- Data as of 2026-08-30T08:39:29.467469+00:00.