+22
Daily
+308
Weekly
+829
Monthly
27,839
stars
3,746
forks
158
watchers
222
prs
351
issues
1
releases
README
!Chatterbox Multilingual Image Chatterbox TTS [!IMPORTANT] As of August 2026, Chatterbox is retired research and is no longer maintained. Resemble AI does not sell text-to-speech, voice cloning, or any other voice AI product, and this repository is not a Resemble AI product. The code stays public as an archive under the MIT license, with no support, updates, or paid tier. Resemble AI now builds AI detection models for deepfakes, synthetic media, and AI agents. Read why we went all in on deepfake detection. Made with ♥️ by Chatterbox is a family of state-of-the-art, open-source text-to-speech models by Resemble AI. Latest Release: Chatterbox Multilingual V3 Chatterbox Multilingual V3 is the latest general-purpose multilingual TTS model in the Chatterbox family. It keeps the same 0.5B model size while improving speaker similarity, reducing hallucinations, and producing more natural, conversational speech across languages. V3 is designed for broad language coverage like V2, but with stronger stability and more expressive generation. It is the recommended multilingual model for users who want one voice cloning model that works across many languages. Alongside V3, we are releasing the Single Language Pack: dedicated finetunes for priority languages where tighter quality control, stronger language-specific behavior, and more specialized speech generation are valuable. - Broad Multilingual Coverage: Designed as the main general-purpose multilingual Chatterbox model, supporting wide language coverage similar to V2. - Single Language Pack: Dedicated single-language models provide stronger specialization and quality control where language- and regional-dialect-specific performance matters most. - More Consistent Speaker Similarity: Improves voice identity and accent preservation across languages, making cross-language voice cloning more stable and reliable. - Reduced Hallucination: V3 is optimized to reduce unwanted continuation, repetition, and off-prompt speech, especially in cases where earlier multilingual models were less stable. For low-latency English voice agents, Chatterbox-Turbo is our most efficient model. Built on a streamlined 350M parameter architecture, Turbo delivers high-quality speech with less compute and VRAM than our previous models. We have also distilled the speech-token-to-mel decoder, previously a bottleneck, reducing generation from 10 steps to just one, while retaining high-fidelity audio output. Paralinguistic tags are now native to the Turbo model, allowing you to use [cough], [laugh], [chuckle], and more to add distinct realism. While Turbo was built primarily for low-latency voice agents, it excels at narration and creative workflows. For the most resource-constrained deployments, Chatterbox-Nano shares Turbo's architecture in an even smaller 110M parameter package. It targets on-device and CPU inference — running 3x faster than realtime on 8 CPU cores — while keeping the same single-step decoder an
Top issues
#174🚀 Proposal: Optimize Data Preprocessing for >4x Faster TTS Training34 comments · 2025-06-20#193Ways to reduce latency31 comments · 2025-07-07#32finetuning code?26 comments · 2025-05-28#38New languages?23 comments · 2025-05-28#127Performance issues19 comments · 2025-06-06#198TypeError: 'NoneType' object is not callable when initializing ChatterboxTTS17 comments · 2025-07-16#97Gibberish and hallucinations with short segments14 comments · 2025-05-31#51They clones sound Indian.13 comments · 2025-05-29
Latest release
v0.1.2 v0.1.2 2025-06-13What's Changed Example for use in mac M by @serome111 in https://github.com/resemble-ai/chatterbox/pull/40 Update Readme Acknowledgements by @fatchord in https://github.com/resemble-ai/chatterbox/pull/57 Feature: Add cpu mps support by @benpbolton in https://github.com/resemble-ai/chatterbox/pull/35 Add discord to Readme by @TediPapajorgji in https://github.com/resemble-ai/chatterbox/pull/75 update models from pt to safetensors by @manmay-nakhashi in https://github.com/resemble-ai/chatterbox/pull/81 Apply CFG optionally by @jin9581 in https://github.com/resemble-ai/chatterbox/pull/
News & coverage (8)
Hacker NewsChatterbox TTS▲ 670 · 188 comments · 2025-06-11Hacker NewsChatterbox, Resemble AI's production-grade open source TTS model▲ 6 · 1 comments · 2025-05-31Hacker NewsChatterbox – open-source TTS model▲ 5 · 0 comments · 2025-05-28Hacker NewsChatterbox▲ 2 · 0 comments · 2025-06-05Resemble AIChatterbox Multilingual v3: TTS with embedded watermarking for 21 languages and 4 dialects2026-06-10Tech TimesVoicebox Clones Any Voice From 3 Seconds of Audio, Runs Locally for Free, and Has No Consent Lock2026-05-19MarkTechPostMeet Chatterbox Multilingual: An Open-Source Zero-Shot Text To Speech (TTS) Multilingual Model with Emotion Control and Watermarking2025-09-05YouTubeAI clone Homer Simpson using ComfyUI Wan 2.1 best guide install Workflow2025-07-19