Coqui TTS coqui-ai/TTS

Python TTS library with many models (XTTS-v2, VITS, YourTTS, Bark, Tortoise); original repo unmaintained, continued by idiap fork.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

Coqui TTS at a glance

Checked 15 Oct 2026

Toolkit for training and running TTS, including XTTS-v2 multilingual voice cloning and ~1100-language Fairseq models. Code is MPL-2.0, but XTTS-v2 weights use the Coqui Public Model License, which allows non-commercial use only. The original coqui-ai/TTS repo has not been pushed since August 2024 (not archived) and coqui.ai returns 404; the idiap fork (PyPI package coqui-tts) is maintained and adds macOS and Windows wheels. Hardware needs are not documented.

Cite this pageRepoQuarry. “Coqui TTS.” Checked 15 Oct 2026. https://repoquarry.dev/projects/coqui-tts

How much of ElevenLabs does it replace?

2 of 4 jobs. Multilingual TTS and zero-shot cloning via XTTS-v2, but XTTS-v2 weights are non-commercial only and the original repo is unmaintained (use the idiap fork).

Speech generation Partial replacement

Voice cloning Partial replacement

Speech recognition Not covered

Voice agents Not covered

For speech recognition, voice agents, see other ElevenLabs alternatives. You may also need to build an interface, an API server and hosting yourself.

How much of Descript does it replace?

2 of 3 jobs. Voice cloning and text-to-speech only; no transcript-based audio or video editing.

Transcript-based editing Not covered

Voice cloning Partial replacement

Speech generation Partial replacement

For transcript-based editing, see other Descript alternatives. You may also need to build an interface, an API server and hosting yourself.

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction

QuestionAnswerSourceChecked

Runs on my machine? Yes, Python library and CLI on CPU or GPU, plus a CPU Docker image You can also try TTS without install with the docker image. github.com · TTS#docker-image ↗ 1d ago

Code licence MPL-2.0 (weak copyleft, file-level) Mozilla Public License Version 2.0 github.com · LICENSE.txt ↗ 1d ago

Model weights licence Varies per model; the flagship XTTS-v2 weights use the Coqui Public Model License 1.0.0, non-commercial only. Licences of the other bundled models were not checked. This license allows only non-commercial use of a machine learning model and its outputs. huggingface.co · XTTS-v2 ↗ 1d ago

Commercial use Code is usable commercially under MPL-2.0, but XTTS-v2 (the main voice cloning model) is non-commercial only, including its outputs; other models carry their own licences Non-commercial purposes include any of the following uses of the model or its output, but only so far as you do not receive any direct or indirect payment arising from the use of the model or its output. huggingface.co · LICENSE.txt ↗ 1d ago

Paid services needed? None required If you are only interested in synthesizing speech with the released TTS models, installing from PyPI is the easiest option. github.com · TTS#installation ↗ 1d ago

Hardware No RAM or VRAM requirements documented; code falls back to CPU when CUDA is unavailable and a CPU Docker image exists docker run --rm -it -p 5002:5002 --entrypoint /bin/bash ghcr.io/coqui-ai/tts-cpu github.com · TTS#docker-image ↗ 1d ago

Operating systems Original repo tested on Ubuntu only, with a third-party Windows guide; the idiap fork publishes wheels for Linux, macOS and Windows TTS is tested on Ubuntu 18.04 with python >= 3.9, < 3.12. github.com · TTS#installation ↗ 1d ago

Setup effort Easy, pip install TTS (original; Python 3.9-3.11) or pip install coqui-tts (maintained fork) pip install TTS github.com · TTS#installation ↗ 1d ago