Model · Coqui · Text-To-Speech
Coqui XTTS v2
Coqui's open multilingual TTS, voice cloning from a 6-second sample across 17 languages. Once the leading open alternative to ElevenLabs; the company has closed and the licence bars commercial use.
- Modality
- Text-To-Speech
- License
- Coqui Public Model License (Open weights)
- Released
- November 1, 2023
- Last verified
- October 28, 2026
- Runs locally
- Yes
Strengths
- Open weights — fully self-hostable
- Voice cloning with short samples
- 17 languages
Weaknesses
- Coqui (the company) shut down — community maintenance only
- Quality below ElevenLabs at the very high end
- Coqui Public Model License does not allow commercial use, and no one can now grant a commercial licence
Try it
| Where | Type | Notes |
|---|---|---|
| Hugging Face | weights | Coqui Public Model License |
| GitHub | local | Reference implementation; dormant since 2024-08 |
Official sources
- Model card model
Change log
- — Deprecated — company closed, no direct successor. coqui.ai showed 'Coqui is shutting down' by 2024-01-03 (Wayback Machine: absent on 2023-12-25, present on 2024-01-03; GitHub issue #3488 'next steps after shutdown' opened the same day). The coqui-ai/TTS repo was last pushed 2024-08-16. No superseded_by because no Coqui successor exists; VoxCPM2, Chatterbox and Qwen3-TTS are the current open alternatives. The weights still show 6.1M Hugging Face downloads/month.
- — Verified: the weights remain hosted, ungated and heavily used (7.2M downloads last month) despite Coqui the company being defunct — this entry's existing 'community maintenance only' weakness is accurate. Maintenance has moved to idiap/coqui-ai-TTS.
- — Initial entry.
Esc