utOpenBMB · Downloadable
VoxCPM1.5
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Dec 5, 2025
- Parameters
- 801.7M
- 4-bit weights only
- ≈ 0.4 GB
- License
- apache-2.0
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 recordsMicrosoft · Downloadable
VibeVoice-Realtime-0.5B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Dec 4, 2025
- Parameters
- 500M
- 4-bit weights only
- ≈ 0.3 GB
- License
- mit
Meta · Downloadable
omniASR-LLM-7B-ZS
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- apache-2.0
Meta · Downloadable
omniASR-LLM-7B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- apache-2.0
Meta · Downloadable
omniASR-LLM-3B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 3B
- 4-bit weights only
- ≈ 1.5 GB
- License
- apache-2.0
Meta · Downloadable
omniASR-LLM-1B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 1B
- 4-bit weights only
- ≈ 0.5 GB
- License
- apache-2.0
Meta · Downloadable
omniASR-LLM-300M
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 300M
- 4-bit weights only
- ≈ 0.2 GB
- License
- apache-2.0
Meta · Downloadable
omniASR-CTC-7B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- apache-2.0
Meta · Downloadable
omniASR-CTC-3B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 3B
- 4-bit weights only
- ≈ 1.5 GB
- License
- apache-2.0
Meta · Downloadable
omniASR-CTC-1B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 1B
- 4-bit weights only
- ≈ 0.5 GB
- License
- apache-2.0
Meta · Downloadable
omniASR-CTC-300M
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 300M
- 4-bit weights only
- ≈ 0.2 GB
- License
- apache-2.0
Meta · Downloadable
omniASR-W2V-7B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- apache-2.0
Meta · Downloadable
omniASR-W2V-3B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 3B
- 4-bit weights only
- ≈ 1.5 GB
- License
- apache-2.0
Meta · Downloadable
omniASR-W2V-1B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 1B
- 4-bit weights only
- ≈ 0.5 GB
- License
- apache-2.0
Meta · Downloadable
omniASR-W2V-300M
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 27, 2025
- Parameters
- 300M
- 4-bit weights only
- ≈ 0.2 GB
- License
- apache-2.0
StepFun · Downloadable
Step-Audio-R1
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 18, 2025
- Parameters
- 33.5B
- 4-bit weights only
- ≈ 16.7 GB
- License
- apache-2.0
Supertone · Downloadable
supertonic
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 18, 2025
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- openrail
Mistral AI · Downloadable
Voxtral-4B-TTS-2603
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Nov 17, 2025
- Parameters
- 4B
- 4-bit weights only
- ≈ 2 GB
- License
- cc-by-nc-4.0
OpenMOSS · Downloadable
MOSS-TTSD-v0.7
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Oct 31, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- apache-2.0
Tencent · Downloadable
SongPrep-7B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 19, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- Not disclosed
OpenBMB · Downloadable
VoxCPM-0.5B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Sep 16, 2025
- Parameters
- 500M
- 4-bit weights only
- ≈ 0.3 GB
- License
- apache-2.0
Qwen · Alibaba · Cloud
Qwen3-Omni Flash
Cloud API for vision, video understanding, audio understanding, audio generation, chat & writing, reasoning, tool use. Capabilities are catalog-listed, not independently scored.
- Source listed
- Sep 15, 2025
- License
- Provider terms
Liquid AI · Downloadable
LFM2-Audio-1.5B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Aug 28, 2025
- Parameters
- 1.5B
- 4-bit weights only
- ≈ 0.8 GB
- License
- other
Microsoft · Downloadable
VibeVoice-1.5B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Aug 25, 2025
- Parameters
- 1.5B
- 4-bit weights only
- ≈ 0.8 GB
- License
- mit
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.