Category ranking · 7 models · checked 2026-10-13
Text to speech
Ranked by No common public benchmark captured yet. Source: —.
No common public benchmark captured yet
No model in this category has a comparable public score yet.
# | Model | Parameters | Score | Source | Licence |
|---|---|---|---|---|---|
| — | Chatterbox Resemble AI | — | Not yet measured | — | MIT |
| — | CSM 1B Sesame | 1.6 B | Not yet measured | — | Apache-2.0 |
| — | Dia 1.6B Nari Labs | 1.6 B | Not yet measured | — | Apache-2.0 |
| — | Kokoro 82M hexgrad | — | Not yet measured | — | Apache-2.0 |
| — | OpenAudio S1 mini Fish Audio | — | Not yet measured | — | CC-BY-NC-SA-4.0 Check terms before commercial use |
| — | Orpheus 3B Canopy Labs | 3.8 B | Not yet measured | — | Apache-2.0 |
| — | VibeVoice 1.5B Microsoft | 2.7 B | Not yet measured | — | MIT |
How to read this: one public benchmark per category, so you can compare like with like. We copy the published number and link it; we do not re-run it, average different benchmarks or fill gaps. Vendor-reported numbers use each vendor's own settings, so treat small gaps as ties. “Not yet measured” means we found no comparable public score, not that the model is weak.
Every model was checked against the Hugging Face API on 2026-10-13: it exists, is public, and has the parameter count and licence shown. Other categories: Math and reasoning · Coding · Vision-language · OCR and documents · Speech to text · Image generation · Embeddings and rerankers · Small fast 'System 1' · Biomedical · Tool use and agents · Multilingual and translation · Time series · Robotics (VLA).
Machine-readable: /api/v1/categories/text-to-speech.json