1,426 models · 1,226 open weights · 200 API-only · refreshed nightly

Audio text to text models

Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

All 1,426 Open weights (self-host) 1,226 API-only 200

All text-generation 720 text-to-image 165 image-text-to-text 112 ASR 86 sentence-similarity 64 translation 56 text-classification 51 feature-extraction 48 image-classification 39 text-to-speech 23 token-classification 21 audio-classification 12 image-segmentation 11 summarization 8 object-detection 8 audio-text-to-text 1 any-to-any 1

Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB

1 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
01	Voxtral-Small-24B-2507 mistralai · audio-text-to-text Open weights Also via API	24.3 B	—	✓ apache-2.0	18 K	from 110.9 GB

VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.