utTencent · Downloadable
HunyuanVideo-Foley
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Aug 21, 2025
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- other
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 recordsKyutai · Downloadable
tts-0.75b-en-public
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jul 15, 2025
- Parameters
- 750M
- 4-bit weights only
- ≈ 0.4 GB
- License
- cc-by-4.0
OpenMOSS · Downloadable
MOSS-TTSD-v0.5
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jul 4, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- apache-2.0
Mistral AI · Downloadable
Voxtral-Small-24B-2507
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jul 1, 2025
- Parameters
- 24B
- 4-bit weights only
- ≈ 12 GB
- License
- apache-2.0
Kyutai · Downloadable
tts-1.6b-en_fr
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jun 30, 2025
- Parameters
- 1.6B
- 4-bit weights only
- ≈ 0.8 GB
- License
- cc-by-4.0
Kyutai · Downloadable
stt-1b-en_fr-trfs
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jun 25, 2025
- Parameters
- 1B
- 4-bit weights only
- ≈ 0.5 GB
- License
- cc-by-4.0
Kyutai · Downloadable
stt-2.6b-en-trfs
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jun 25, 2025
- Parameters
- 2.6B
- 4-bit weights only
- ≈ 1.3 GB
- License
- cc-by-4.0
OpenMOSS · Downloadable
MOSS-TTSD-v0
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jun 19, 2025
- Parameters
- 2B
- 4-bit weights only
- ≈ 1 GB
- License
- apache-2.0
Kyutai · Downloadable
stt-1b-en_fr
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jun 17, 2025
- Parameters
- 1B
- 4-bit weights only
- ≈ 0.5 GB
- License
- cc-by-4.0
Kyutai · Downloadable
stt-1b-en_fr-candle
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jun 17, 2025
- Parameters
- 1B
- 4-bit weights only
- ≈ 0.5 GB
- License
- cc-by-4.0
Kyutai · Downloadable
stt-2.6b-en-candle
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jun 17, 2025
- Parameters
- 2.6B
- 4-bit weights only
- ≈ 1.3 GB
- License
- cc-by-4.0
k2-fsa · Downloadable
ZipVoice
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jun 15, 2025
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- Not disclosed
Kyutai · Downloadable
stt-2.6b-en
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Jun 6, 2025
- Parameters
- 2.6B
- 4-bit weights only
- ≈ 1.3 GB
- License
- cc-by-4.0
Fish Audio · Downloadable
s1-mini
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- May 31, 2025
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- cc-by-nc-sa-4.0
Stability AI · Downloadable
stable-audio-open-small
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- May 12, 2025
- Parameters
- 497.2M
- 4-bit weights only
- ≈ 0.2 GB
- License
- other
Google · Preview
Gemini 2.5 Flash Preview TTS
Cloud API for audio generation. Capabilities are catalog-listed, not independently scored.
- Source listed
- May 1, 2025
- License
- Provider terms
Google · Preview
Gemini 2.5 Pro Preview TTS
Cloud API for audio generation. Capabilities are catalog-listed, not independently scored.
- Source listed
- May 1, 2025
- License
- Provider terms
Moonshot AI · Downloadable
Kimi-Audio-7B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Apr 25, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- mit
Moonshot AI · Downloadable
Kimi-Audio-7B-Instruct
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Apr 25, 2025
- Parameters
- 7B
- 4-bit weights only
- ≈ 3.5 GB
- License
- mit
pyannote · Downloadable
speaker-diarization-community-1
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Apr 15, 2025
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- cc-by-4.0
k2-fsa · Downloadable
TTS_eval_models
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Apr 3, 2025
- Parameters
- Not reported
- 4-bit weights only
- Not reported
- License
- apache-2.0
Microsoft · Downloadable
Phi-4-multimodal-instruct
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Feb 24, 2025
- Parameters
- 5.6B
- 4-bit weights only
- ≈ 2.8 GB
- License
- mit
StepFun · Downloadable
Step-Audio-TTS-3B
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Feb 13, 2025
- Parameters
- 3B
- 4-bit weights only
- ≈ 1.5 GB
- License
- apache-2.0
StepFun · Downloadable
Step-Audio-Chat
Works with speech or audio. Check the model card for transcription and generation capabilities.
- Source listed
- Feb 13, 2025
- Parameters
- 131.9B
- 4-bit weights only
- ≈ 66 GB
- License
- apache-2.0
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.