WHAT’S NEW

New AI models.
Keep up without the noise.

The latest source listings from makers we track, covering language, images, video, audio, and 3D. Catalog checked Sep 10, 2026.

Sorted by the date a source repository was created, which may precede public release. This is a feed of new listings, not confirmed release announcements. Downloadable weights do not automatically mean an open-source license. Coverage and date meanings.

Audio listings

62 dated records

Microsoft · Downloadable

VibeVoice-ASR-Streaming-1.5B

TranscriptionAudio understanding

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Sep 2, 2026
Parameters
1.5B
4-bit weights only
≈ 0.8 GB
License
mit
Compare this model →

Microsoft · Downloadable

VibeVoice-ASR-Streaming-7B

TranscriptionAudio understanding

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Sep 2, 2026
Parameters
7B
4-bit weights only
≈ 3.5 GB
License
mit
Compare this model →

MiniMax · Downloadable

MiniMax-Music3

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Aug 7, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
Not disclosed
Compare this model →

Microsoft · Downloadable

VibeVoice-ASR-BitNet

TranscriptionAudio understanding

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Jul 24, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
mit
Compare this model →

Lightricks · Downloadable

LTX-2.3-22b-LoRA-Foley-V2A

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Jul 15, 2026
Parameters
22B
4-bit weights only
≈ 11 GB
License
other
Compare this model →

Qwen · Alibaba · Downloadable

Qwen3-ASR-0.6B-hf

TranscriptionAudio understanding

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Jun 26, 2026
Parameters
600M
4-bit weights only
≈ 0.3 GB
License
apache-2.0
Compare this model →

Qwen · Alibaba · Downloadable

Qwen3-ASR-1.7B-hf

TranscriptionAudio understanding

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Jun 26, 2026
Parameters
1.7B
4-bit weights only
≈ 0.9 GB
License
apache-2.0
Compare this model →

Google · Downloadable

magenta-realtime-2

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
May 28, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
cc-by-4.0
Compare this model →

Stability AI · Downloadable

stable-audio-3-optimized

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
May 18, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
other
Compare this model →

Stability AI · Downloadable

stable-audio-3-small-music

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
May 17, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
other
Compare this model →

Stability AI · Downloadable

stable-audio-3-small-sfx

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
May 17, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
other
Compare this model →

Stability AI · Downloadable

stable-audio-3-medium

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
May 17, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
other
Compare this model →

Stability AI · Downloadable

stable-audio-3-medium-base

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
May 17, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
other
Compare this model →

Stability AI · Downloadable

stable-audio-3-small-sfx-base

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
May 17, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
other
Compare this model →

Stability AI · Downloadable

stable-audio-3-small-music-base

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
May 16, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
other
Compare this model →

NVIDIA · Downloadable

nemotron-3.5-asr-streaming-0.6b

TranscriptionEmbeddingsAudio understanding

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
May 15, 2026
Parameters
600M
4-bit weights only
≈ 0.3 GB
License
other
Compare this model →

NVIDIA · Downloadable

Real-time_RE-USE

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Apr 14, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
other
Compare this model →

NVIDIA · Downloadable

parakeet-unified-en-0.6b

TranscriptionAudio understanding

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Apr 7, 2026
Parameters
600M
4-bit weights only
≈ 0.3 GB
License
other
Compare this model →

NVIDIA · Downloadable

audio-flamingo-next-think-hf

Capabilities unconfirmed

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Apr 5, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
other
Compare this model →

NVIDIA · Downloadable

audio-flamingo-next-hf

Capabilities unconfirmed

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Apr 5, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
other
Compare this model →

NVIDIA · Downloadable

RE-USE

Audio generation

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Mar 17, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
other
Compare this model →

Microsoft · Downloadable

VibeVoice-ASR-HF

Transcription

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Mar 2, 2026
Parameters
Not reported
4-bit weights only
Not reported
License
mit
Compare this model →

Qwen · Alibaba · Downloadable

Qwen3-ForcedAligner-0.6B

TranscriptionAudio understanding

Works with speech or audio. Check the model card for transcription and generation capabilities.

Source listed
Jan 28, 2026
Parameters
600M
4-bit weights only
≈ 0.3 GB
License
apache-2.0
Compare this model →

What makes this feed useful?

Capability tags distinguish a model that reads images from one that creates them. Each listing links to its source and a permanent profile, so you can inspect its license and compare it with a model you already know.

Does this cover every new release?

No. The current feed tracks public Hugging Face metadata from selected makers. It can miss untracked makers, cloud-only releases, and records beyond a source’s retrieval limit. Announced models without a source listing are not included. Check Sources & methodology for the current coverage.

Listings update with the catalog automatically. A missing or delayed source can leave older information visible; each model profile shows when it was checked.