resemble-ai/chatterbox

Health v2 · maintenance only

Adoption not part of the score

26163 stars · 3518 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity active

tts speech-recognition machine-learning llm-inference speech-processing artificial-intelligence deep-learning python cross-platform voice-cloning zero-shot-tts multilingual emotion-control paralinguistic-tags open-weights audio gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="resemble-ai/chatterbox")