Coqui TTS
Open-source deep learning toolkit for text-to-speech
FreeVoiceOpen Source2 impressions
Coqui TTS is a free alternative to ElevenLabs.
Coqui AI TTS is an open-source library for advanced text-to-speech generation and voice conversion.
- for
- Researchers and developers building speech synthesis or voice-cloning applications.
- pricing
- open source
- license
- MPL-2.0
Key features
- Pretrained multilingual models — Access over 1100 language models ready for inference.
- Model training tools — Fast training with terminal and TensorBoard logs.
- Voice conversion & cloning — Convert or clone voices using FreeVC, kNN-VC, OpenVoice.
- Dataset curation utilities — Tools for analyzing and preparing TTS datasets.
- Python & CLI APIs — Use TTS via a Python library or command-line interface.
- Docker support — Run the library in a container without local installation.
Use cases
- Generate speech for virtual assistants in multiple languages
- Fine-tune a custom TTS model on proprietary data
- Clone a brand’s voice for automated announcements
- Convert recorded speech to a different speaker’s voice
- Curate and analyze large speech datasets for research
Coqui TTS vs alternatives
 Coqui TTS |  ElevenLabs |  Piper TTS |  Otter.ai | |
|---|---|---|---|---|
| Best for | Open-source multilingual TTS | Hosted voice cloning | Lightweight local TTS | Speech transcription |
| Pricing | Open source | Subscription | Free | Subscription |
| DevHunt upvotes | 0 | 0 | 0 | 0 |
| Launched | — | — | — | — |
- Coqui TTS vs ElevenLabs: ElevenLabs offers hosted TTS with commercial licensing, while Coqui is self-hosted and open source.
- Coqui TTS vs Piper TTS: Piper TTS focuses on fast local inference, whereas Coqui provides a broader model zoo and training tools.
- Coqui TTS vs Otter.ai: Otter.ai provides transcription, not synthesis; Coqui generates speech from text.
Coqui TTS FAQ
How do I install Coqui TTS?+
Install PyTorch first, then run uv pip install coqui-tts or clone the repo and install with uv pip install -e .
Can I run Coqui TTS on Windows?+
Yes, the library supports Linux, macOS and Windows with Python 3.10-3.14 and PyTorch 2.2+.
Where can I find pretrained models?+
Models are listed on the documentation and can be listed programmatically via TTS().list_models().
How do I use voice cloning?+
Use a single-speaker TTS model together with the default FreeVC voice-conversion model, providing a speaker_wav reference.
Is there a Docker image?+
Yes, ghcr.io/idiap/coqui-tts-cpu provides a ready-to-run server; GPU images are also documented.
How are optional dependencies installed?+
Use extras, e.g., uv pip install coqui-tts[server,ja] to add server and Japanese G2P support.
Summarized by DevHunt from github.com · Oct 7, 2026. Details may change; check the official site.
About this listing
DevHunt lists Coqui TTS because developers expect to find it next to the tools in its category. It did not launch on DevHunt. Work on Coqui TTS? Message us to claim this listing.
