- Home
- Text-to-speech tools
- Chatterbox TTS
Chatterbox TTS
Chatterbox TTS · 812 W Dana St, Mountain View, CA 94041, United States · founded 2019
What it is
Chatterbox TTS is a family of open-source text-to-speech models from Resemble AI, offered free under the MIT license for research and development. The project lists Turbo, Nano, Multilingual V3, and dedicated single-language models. Turbo is intended for low-latency voice agents and accepts tags such as [sigh], [gasp], [cough], and [laugh] to prompt vocal reactions. Nano is aimed at on-device or CPU inference when memory and latency budgets are tight. The README lists 23 languages for Multilingual and gives installation instructions for pip and source installation. It describes development with Python 3.11 on Debian 11, with CUDA, CPU, and MPS device options. Chatterbox supports voice cloning, batch processing, voice isolation, audio input, and WAV export. Each generated audio file includes Resemble AI’s PerTh watermark. Resemble says it has stopped offering voice generation as a commercial product, while its models remain open and free for research and development. The project invites users to join its Discord community.
For and against
For
- Free under the MIT license for research and development.
- Includes Turbo, Nano, Multilingual V3, and single-language models.
- Multilingual lists support for 23 languages.
- Supports voice cloning and WAV export.
- Offers CUDA, CPU, and MPS device options.
Against
- Generated audio includes the PerTh watermark.
- Resemble has stopped offering voice generation as a commercial product.
- The listed platforms are Linux, macOS, and self-hosted.
The verdict
Chatterbox TTS offers several model options, including speech prompting in Turbo and multilingual support. Its free research-and-development availability and PerTh watermark are important considerations for prospective users.
Who it suits
Chatterbox TTS suits developers exploring open-source speech generation for research and development. Turbo targets low-latency voice agents, while Nano is intended for on-device or CPU use with tight memory and latency budgets.
Plans and prices
Voice AI Research (Chatterbox)
Open models · free to build on · no commercial hosted voice service
Read 21 Oct 2026 · docs.resemble.ai
Chatterbox open-source models
Open-source models for research and development
Read 8 Oct 2026 · github.com
On the record
- Commercial use
- Yesgithub.com · read 20 Sep 2026
- Company founding
- Resemble says Zohaib Ahmed and Saqib Muhammad started the company in 2019.resemble.ai · read 21 Oct 2026
- Company headquarters
- LinkedIn lists Resemble AI headquarters in Santa Clara, California, with 11–50 employees.linkedin.com · read 21 Oct 2026
- Company ownership and funding
- Crunchbase describes Resemble AI as a private, for-profit company with five funding rounds and founders Zohaib Ahmed and Saqib Muhammad, while funding amounts are obscured.crunchbase.com · read 21 Oct 2026
- Controls
- The Python interface exposes generation controls including exaggeration, CFG weight, temperature and random seed.raw.githubusercontent.com · read 21 Oct 2026
- Current availability
- Resemble says it has stopped offering voice generation as a commercial product and that its voice models remain open and free for research and development.resemble.ai · read 8 Oct 2026
- Documentation depth
- The repository includes model selection tables, Python examples, language identifiers, watermark extraction code, tuning guidance and evaluation links.raw.githubusercontent.com · read 21 Oct 2026
- Export formats
- WAVgithub.com · read 20 Sep 2026
- Expressive speech
- Turbo supports paralinguistic tags such as [sigh], [gasp], [cough], and [laugh] to prompt vocal reactions.resemble.ai · read 8 Oct 2026
- Hallucination reduction
- The V3 description says it reduces unwanted continuation, repetition and off-prompt speech compared with earlier multilingual versions.raw.githubusercontent.com · read 21 Oct 2026
- Installation
- The project can be installed with pip as chatterbox-tts or from a cloned repository in editable mode.ondalabs.app · read 21 Oct 2026
- Integration
- NVIDIA provides a Chatterbox TTS plugin for ACE for Games with CUDA, Vulkan and Windows D3D12 backends.docs.nvidia.com · read 21 Oct 2026
- Intended users
- The README describes Turbo for low-latency voice agents and Nano for on-device or CPU inference when memory and latency budgets are tight.github.com · read 8 Oct 2026
- Languages
- The README lists 23 supported languages for Chatterbox Multilingual.github.com · read 8 Oct 2026
- Latest model
- The repository identifies Chatterbox Multilingual V3 as its newest general-purpose multilingual model.raw.githubusercontent.com · read 21 Oct 2026
- License
- The code and model listing identify the project as MIT licensed, permitting modification and redistribution subject to the license notice.github.com · read 21 Oct 2026
- Limit: commercial availability
- Resemble’s current product notice says voice generation is no longer offered as a commercial product, although the models remain open and free for research and development.resemble.ai · read 21 Oct 2026
- Limit: comparative performance evidence
- An independent review reports that Resemble’s blind test favored Chatterbox, but an Artificial Analysis snapshot ranked Chatterbox below ElevenLabs’ leading model.ondalabs.app · read 21 Oct 2026
