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 Oct 28, 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

172 dated records

OpenMOSS · Downloadable

MOSS-Audio-4B-Thinking

Capabilities unconfirmed

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

Source listed
Apr 11, 2026
Parameters
4B
4-bit weights only
≈ 2 GB
License
apache-2.0
Compare this model →

OpenMOSS · Downloadable

MOSS-Audio-4B-Instruct

Capabilities unconfirmed

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

Source listed
Apr 10, 2026
Parameters
4B
4-bit weights only
≈ 2 GB
License
apache-2.0
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
8.3B
4-bit weights only
≈ 4.1 GB
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
8.3B
4-bit weights only
≈ 4.1 GB
License
other
Compare this model →

Tencent · Downloadable

Unified_Audio_Schema

Transcription

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

Source listed
Apr 3, 2026
Parameters
8.3B
4-bit weights only
≈ 4.2 GB
License
other
Compare this model →

OpenBMB · Downloadable

VoxCPM2

Audio generation

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

Source listed
Apr 3, 2026
Parameters
2.3B
4-bit weights only
≈ 1.1 GB
License
apache-2.0
Compare this model →

OpenMOSS · Downloadable

MOSS-TTS-Nano-100M

Audio generation

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

Source listed
Apr 2, 2026
Parameters
100M
4-bit weights only
≈ 0.1 GB
License
apache-2.0
Compare this model →

k2-fsa · Downloadable

OmniVoice-Emilia

Audio generation

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

Source listed
Mar 30, 2026
Parameters
612.6M
4-bit weights only
≈ 0.3 GB
License
Not disclosed
Compare this model →

k2-fsa · Downloadable

OmniVoice

Audio generation

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

Source listed
Mar 30, 2026
Parameters
612.6M
4-bit weights only
≈ 0.3 GB
License
Not disclosed
Compare this model →

Google · Preview

Gemini 3.1 Flash Live Preview

VisionVideo understandingAudio understandingAudio generationReasoningTool use

Cloud API for vision, video understanding, audio understanding, audio generation, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.

Source listed
Mar 26, 2026
License
Provider terms
Compare this model →

Google · Preview

Lyria 3 Clip Preview

VisionAudio generation

Cloud API for vision, audio generation, chat & writing. Capabilities are catalog-listed, not independently scored.

Source listed
Mar 25, 2026
License
Provider terms
Compare this model →

Google · Preview

Lyria 3 Pro Preview

VisionAudio generation

Cloud API for vision, audio generation, chat & writing. Capabilities are catalog-listed, not independently scored.

Source listed
Mar 25, 2026
License
Provider terms
Compare this model →

Kyutai · Downloadable

moshika-rag-candle

Audio generation

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

Source listed
Mar 19, 2026
Parameters
8.4B
4-bit weights only
≈ 4.2 GB
License
cc-by-4.0
Compare this model →

Kyutai · Downloadable

moshika-rag-pytorch

Audio generation

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

Source listed
Mar 19, 2026
Parameters
7.7B
4-bit weights only
≈ 3.9 GB
License
cc-by-4.0
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
9.6M
4-bit weights only
≈ 0 GB
License
other
Compare this model →

Tencent · Downloadable

Covo-Audio-Chat

Audio generation

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

Source listed
Mar 16, 2026
Parameters
8.4B
4-bit weights only
≈ 4.2 GB
License
Not disclosed
Compare this model →

Fish Audio · Downloadable

s2-pro

Audio generation

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

Source listed
Mar 9, 2026
Parameters
4.6B
4-bit weights only
≈ 2.3 GB
License
other
Compare this model →

inclusionAI · Downloadable

Ming-omni-tts-tokenizer-12Hz

Audio generation

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

Source listed
Feb 11, 2026
Parameters
780.4M
4-bit weights only
≈ 0.4 GB
License
apache-2.0
Compare this model →

inclusionAI · Downloadable

Ming-omni-tts-0.5B

Audio generation

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

Source listed
Feb 11, 2026
Parameters
500M
4-bit weights only
≈ 0.3 GB
License
apache-2.0
Compare this model →

inclusionAI · Downloadable

Ming-omni-tts-16.8B-A3B

Audio generation

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

Source listed
Feb 11, 2026
Parameters
16.8B
4-bit weights only
≈ 8.4 GB
License
apache-2.0
Compare this model →

Kyutai · Downloadable

hibiki-zero-3b-pytorch

Audio generation

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

Source listed
Feb 9, 2026
Parameters
3B
4-bit weights only
≈ 1.5 GB
License
Not disclosed
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.