Model card
XTTS v2.
Coqui AIopen-sourceUnknown paramsGPT-based TTS with VQ-VAE tokens
Coqui XTTS v2. Multilingual zero-shot TTS in 17 languages. Released Oct 2023.
§ 01 · Benchmarks
Every benchmark XTTS v2 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | LJ Speech | Speech · Text-to-Speech | mos | 4.2% | #5 | 2023-04-03 | source ↗ |
| 02 | VCTK | Speech · Text-to-Speech | mos | 4.1% | #5 | 2023-04-03 | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Papers
1 paper with results for XTTS v2.
- 2023-04-03· Speech· 2 results
XTTS: A Massively Multilingual Zero-Shot Text-to-Speech Model
§ 05 · Sources & freshness
Where these numbers come from.
arxiv
2
results
2 of 2 rows marked verified.