# Coqui TTS

> 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.

- Repository: https://github.com/coqui-ai/TTS
- Official docs: https://tts.readthedocs.io/en/latest/
- Checked: 2026-10-15

## What it replaces
- ElevenLabs: Speech generation, Voice cloning (partial). 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).
- Descript: Voice cloning, Speech generation (partial). Voice cloning and text-to-speech only; no transcript-based audio or video editing.

## Facts, with sources

| Question | Status | Answer | Source | Checked |
|---|---|---|---|---|
| Runs on my machine? | Confirmed | Yes, Python library and CLI on CPU or GPU, plus a CPU Docker image | https://github.com/coqui-ai/TTS#docker-image | 2026-10-15 |
| Code licence | Partial | MPL-2.0 (weak copyleft, file-level) | https://github.com/coqui-ai/TTS/blob/dev/LICENSE.txt | 2026-10-15 |
| Model weights licence | No | 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. | https://huggingface.co/coqui/XTTS-v2 | 2026-10-15 |
| Commercial use | Partial | 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 | https://huggingface.co/coqui/XTTS-v2/blob/main/LICENSE.txt | 2026-10-15 |
| Paid services needed? | Confirmed | None required | https://github.com/coqui-ai/TTS#installation | 2026-10-15 |
| Hardware | Unknown | No RAM or VRAM requirements documented; code falls back to CPU when CUDA is unavailable and a CPU Docker image exists | https://github.com/coqui-ai/TTS#docker-image | 2026-10-15 |
| Operating systems | Partial | Original repo tested on Ubuntu only, with a third-party Windows guide; the idiap fork publishes wheels for Linux, macOS and Windows | https://github.com/coqui-ai/TTS#installation | 2026-10-15 |
| Setup effort | Confirmed | Easy, pip install TTS (original; Python 3.9-3.11) or pip install coqui-tts (maintained fork) | https://github.com/coqui-ai/TTS#installation | 2026-10-15 |

GitHub: 46122 stars, 6167 forks, last push 2024-08-16, archived: no.
---
Source: RepoQuarry (https://repoquarry.dev/projects/coqui-tts). Data licence: CC BY 4.0. Quotes are from project documentation and belong to their authors.